Shu Kong. Department of Computer Science, UC Irvine
|
|
|
- Stephany Byrd
- 5 years ago
- Views:
Transcription
1 Ubiquitous Fine-Grained Computer Vision Shu Kong Department of Computer Science, UC Irvine
2 Outline 1. Problem definition 2. Instantiation 3. Challenge and philosophy 4. Fine-grained classification with holistic representation 5. Fine-grained identification by matching local patches 6. Future work and conclusion
3 Problem Definition 1. Problem definition 2. Instantiation 3. Challenge and philosophy 4. Fine-grained classification with holistic representation 5. Fine-grained identification by matching local patches 6. Future work and conclusion
4 Problem Definition Fine-grained marginally different or subtle
5 Problem Definition Fine-grained marginally different or subtle involving great attention to detail (Oxford dictionary)
6 Problem Definition Fine-grained marginally different or subtle involving great attention to detail (Oxford dictionary)
7 Problem Definition Fine-grained marginally different or subtle involving great attention to detail (Oxford dictionary) The devil is in the details!...and everywhere!
8 Problem definition Fine-grained computer vision distinguish subordinate categories within an entrylevel category
9 Problem definition Fine-grained computer vision distinguish subordinate categories within an entrylevel category tasks are like classification, segmentation, specific case studies, etc.
10 Instantiation -- classification Shu Kong, Charless Fowlkes, "Low-rank Bilinear Pooling for Fine-Grained Classification", arxiv: , 2016
11 Instantiation -- classification Shu Kong, Charless Fowlkes, "Low-rank Bilinear Pooling for Fine-Grained Classification", arxiv: , 2016
12 Instantiation -- classification Shu Kong, Charless Fowlkes, "Low-rank Bilinear Pooling for Fine-Grained Classification", arxiv: , 2016
13 Instantiation -- identification image from Surangi W. Punyasena S. Kong, S. Punyasena, C. Fowlkes, "Spatially Aware Dictionary Learning and Coding for Fossil Pollen Identification", CVPR CVMI, 2016
14 Instantiation -- identification modern pollen grain from glauca fossil pollen pollen grain from glauca S. Kong, S. Punyasena, C. Fowlkes, "Spatially Aware Dictionary Learning and Coding for Fossil Pollen Identification", CVPR CVMI, 2016
15 Instantiation -- segmentation original image semantic segmentation S. Kong, "Automated Biological Image Analysis using Computer Vision and Machine Learning", Janelia workshop, 2016
16 Instantiation -- segmentation original image instance segmentation S. Kong, "Automated Biological Image Analysis using Computer Vision and Machine Learning", Janelia workshop, 2016
17 Instantiation -- segmentation S. Kong, "Automated Biological Image Analysis using Computer Vision and Machine Learning", Janelia workshop, 2016
18 Instantiation -- photo aesthetic ranking 18 S. Kong, X. Shen, Z. Lin, R. Mech, C. Fowlkes, "Photo Aesthetics Ranking Network with Attributes and Content Adaptation", ECCV, 2016
19 Instantiation -- photo aesthetic ranking S. Kong, X. Shen, Z. Lin, R. Mech, C. Fowlkes, "Photo Aesthetics Ranking Network with Attributes and Content Adaptation", ECCV, 2016
20 Instantiation -- photo aesthetic ranking 20 S. Kong, X. Shen, Z. Lin, R. Mech, C. Fowlkes, "Photo Aesthetics Ranking Network with Attributes and Content Adaptation", ECCV, 2016
21 Instantiation -- photo aesthetic ranking S. Kong, X. Shen, Z. Lin, R. Mech, C. Fowlkes, "Photo Aesthetics Ranking Network with Attributes and Content Adaptation", ECCV, 2016
22 Challenge and philosophy 1. Problem definition 2. Instantiation 3. Challenge and philosophy 4. Fine-grained classification with holistic representation 5. Fine-grained identification by matching local patches 6. Future work and conclusion
23 Challenge and philosophy lack of training data costly data collection and annotation
24 Challenge and philosophy lack of training data costly data collection and annotation large numbers of categories
25 Challenge and philosophy lack of training data costly data collection and annotation large numbers of categories >14,000 birds >278,000 butterfly&moth >941,000 insects
26 Challenge and philosophy lack of training data costly data collection and annotation large numbers of categories high intra-class vs. low inter-class variance
27 Challenge and philosophy lack of training data costly data collection and annotation large numbers of categories high intra-class vs. low inter-class variance Caspian Tern Caspian Tern Elegant Tern
28 Challenge and philosophy lack of training data costly data collection and annotation large numbers of categories high intra-class vs. low inter-class variance philosophy finding discriminative parts, and matching them effectively
29 Holistic representation based method 1. Problem definition 2. Instantiation 3. Challenge and philosophy 4. Fine-grained classification with holistic representation 5. Fine-grained identification by matching local patches 6. Future work 7. Conclusion
30 Holistic representation based method recognizing bird species by seeing the photo Red_Winged_Blackbird Brandt_Cormorant Acadian_Flycatcher Yellow_Headed_Blackbird Pelagic_Cormorant Yellow_Billed_Cuckoo
31 Holistic representation based method recognizing bird species by seeing the photo In literature, detecting keypoint/parts and stacking them as holistic representation Red_Winged_Blackbird Brandt_Cormorant Acadian_Flycatcher Yellow_Headed_Blackbird Pelagic_Cormorant Yellow_Billed_Cuckoo picture from Wah et al, 2011
32 Holistic representation based method But, this requires strong-supervised annotation, which is expensive to obtain. picture from Wah et al, 2011
33 Holistic representation based method But, this requires strong-supervised annotation, which is expensive to obtain. Preferably in weakly supervised manner -- solely based on category labels without any part annotation/masks. picture from Wah et al, 2011
34 Holistic representation based method One method for this is called bilinear pooling Lin et al., Bilinear CNN models for fine-grained visual recognition, ICCV, 2015
35 Holistic representation based method One method for this is called bilinear pooling compute second-order statistics of local features, and average them as a single holistic representation Lin et al., Bilinear CNN models for fine-grained visual recognition, ICCV, 2015
36 Holistic representation based method One method for this is called bilinear pooling compute second-order statistics of local features, and average them as a single holistic representation The local features can be activations at hidden layers of a convolutional neural network (CNN) Lin et al., Bilinear CNN models for fine-grained visual recognition, ICCV, 2015
37 Holistic representation based method Bilinear Pooling w h c Lin et al., Bilinear CNN models for fine-grained visual recognition, ICCV, 2015
38 Holistic representation based method Bilinear Pooling w h c Lin et al., Bilinear CNN models for fine-grained visual recognition, ICCV, 2015
39 Holistic representation based method Bilinear Pooling w h c Lin et al., Bilinear CNN models for fine-grained visual recognition, ICCV, 2015
40 Holistic representation based method Bilinear Pooling w h c Lin et al., Bilinear CNN models for fine-grained visual recognition, ICCV, 2015
41 Holistic representation based method Bilinear Pooling w h c Lin et al., Bilinear CNN models for fine-grained visual recognition, ICCV, 2015
42 Holistic representation based method Bilinear Pooling CNN -- training in an end-to-end manner Lin et al., Bilinear CNN models for fine-grained visual recognition, ICCV, 2015
43 Holistic representation based method Low-rank Bilinear Pooling
44 Holistic representation based method Low-rank Bilinear Pooling linear SVM
45 Holistic representation based method Low-rank Bilinear Pooling linear SVM
46 Holistic representation based method Low-rank Bilinear Pooling linear SVM
47 Holistic representation based method Low-rank Bilinear Pooling linear SVM linear SVM in matrix
48 Holistic representation based method Low-rank Bilinear Pooling linear SVM linear SVM in matrix rank-r SVM
49 Low-rank SVM Holistic representation based method
50 Low-rank SVM Holistic representation based method
51 Holistic representation based method When bilinear SVM meets bilinear feature 1. linear SVM 2. linear SVM in matrix
52 Holistic representation based method When bilinear SVM meets bilinear feature 1. linear SVM 2. linear SVM in matrix
53 Holistic representation based method When bilinear SVM meets bilinear feature 1. linear SVM 2. linear SVM in matrix
54 Holistic representation based method When bilinear SVM meets bilinear feature 1. linear SVM 2. linear SVM in matrix
55 Holistic representation based method When bilinear SVM meets bilinear feature 1. linear SVM 2. linear SVM in matrix
56 Holistic representation based method When bilinear SVM meets bilinear feature 1. linear SVM 2. linear SVM in matrix
57 Holistic representation based method When bilinear SVM meets bilinear feature maximum Frobenius norm
58 Holistic representation based method When bilinear SVM meets bilinear feature maximum Frobenius norm no need to compute bilinear features when testing
59 Holistic representation based method When bilinear SVM meets bilinear feature maximum Frobenius norm no need to compute bilinear features when testing 200 classes, then param size is reduced from 200*512*512 to 200*512*8
60 Holistic representation based method explicitly computing bilinear features more efficient useful when hw>m
61 Holistic representation based method classifier co-decomposition -- learning a common factor and class-specific parameters of smaller size
62 Holistic representation based method classifier co-decomposition -- learning a common factor and class-specific parameters of smaller size
63 Holistic representation based method classifier co-decomposition -- learning a common factor and class-specific parameters of smaller size
64 Holistic representation based method Studying the two hyperparameters low dimension m low rank r
65 Holistic representation based method Studying the two hyperparameters -- m and r
66 Holistic representation based method Studying the two hyperparameters -- m and r
67 Holistic representation based method Studying the two hyperparameters -- m and r
68 Holistic representation based method Studying the two hyperparameters -- m and r
69 Holistic representation based method Studying the two hyperparameters -- m and r if 200 classes, then param size is reduced from 200*512*512 (~5.2 x 10e7 single precision) to (200*8* *512) (~2.1 x 10e5 single precision)
70 Holistic representation based method Details on the complexity
71 Holistic representation based method Quantitative evaluation on benchmark datasets
72 Holistic representation based method Quantitative evaluation on benchmark datasets
73 Holistic representation based method Qualitative evaluation for understanding the model
74 Holistic representation based method Qualitative evaluation for understanding the model gradient map --- backpropogating error to input image
75 Holistic representation based method Qualitative evaluation for understanding the model gradient map --- backpropogating error to input image average activation map
76 Holistic representation based method Qualitative evaluation for understanding the model gradient map --- backpropogating error to input image average activation map simplying input image by removing superpixels
77 Holistic representation based method Qualitative evaluation for understanding the model
78 Conclusion Holistic representation based method
79 Holistic representation based method Conclusion 1. a more compact and powerful model by coupling bilinear classifier and bilinear feature for fine-grained classification
80 Holistic representation based method Conclusion 1. a more compact and powerful model by coupling bilinear classifier and bilinear feature for fine-grained classification 2. a new direction for a weakly supervised visual learning
81 Holistic representation based method Conclusion 1. a more compact and powerful model by coupling bilinear classifier and bilinear feature for fine-grained classification 2. a new direction for a weakly supervised visual learning 3. useful for learning interpretable attentions
82 Patch-match based method 1. Problem definition 2. Instantiation 3. Challenge and philosophy 4. Fine-grained classification with holistic representation 5. Fine-grained identification by matching local patches 6. Future work and conclusion
83 Patch-match based method patch-match based approach for pollen grain identification
84 Patch-match based method patch-match based approach for pollen grain identification problem Skilled experts trained for years have to identify by eye image from Surangi W. Punyasena
85 Why do we care about identifying pollen? Pollen grains are ubiquitous and well preserved in the fossil record
86 Why do we care about identifying pollen? Pollen grains are ubiquitous and well preserved in the fossil record Identification of pollen samples allows for analysis of plant biodiversity and evolution, understanding history of long-term climate change, etc...
87 Patch-match based method A specific dataset for this exploration 1. arbitrary viewpoint of the pollen grains
88 Patch-match based method A specific dataset for this exploration 1. arbitrary viewpoint of the pollen grains 2. Large intra-class and small inter-class variation
89 Quantitative Result on Fossil Pollen Why not holistic representation? S. Kong, S. Punyasena, C. Fowlkes, "Spatially Aware Dictionary Learning and Coding for Fossil Pollen Identification", CVPR CVMI, 2016
90 Quantitative Result on Fossil Pollen Why not holistic representation? 1. It is expensive to collect and annotate data. S. Kong, S. Punyasena, C. Fowlkes, "Spatially Aware Dictionary Learning and Coding for Fossil Pollen Identification", CVPR CVMI, 2016
91 Quantitative Result on Fossil Pollen Why not holistic representation? 1. It is expensive to collect and annotate data. 2. There are not enough training data using holistic representation. S. Kong, S. Punyasena, C. Fowlkes, "Spatially Aware Dictionary Learning and Coding for Fossil Pollen Identification", CVPR CVMI, 2016
92 Quantitative Result on Fossil Pollen Why not holistic representation? 1. It is expensive to collect and annotate data. 2. There are not enough training data using holistic representation. S. Kong, S. Punyasena, C. Fowlkes, "Spatially Aware Dictionary Learning and Coding for Fossil Pollen Identification", CVPR CVMI, 2016
93 Quantitative Result on Fossil Pollen Why not holistic representation? 1. It is expensive to collect and annotate data. 2. There are not enough training data using holistic representation. Therefore, it's better to match local patches with geometric constraints. S. Kong, S. Punyasena, C. Fowlkes, "Spatially Aware Dictionary Learning and Coding for Fossil Pollen Identification", CVPR CVMI, 2016
94 our patch-match based method The patch-match method needs images to be alligned
95 in-plate rotation viewpoint calibration perform k-medoids clustering on an affinity graph of training set,
96 in-plate rotation viewpoint calibration perform k-medoids clustering on an affinity graph of training set, where pairwise similarity is based on Euclidean distance of pollen grain silhouette
97 in-plate rotation viewpoint calibration perform k-medoids clustering on an affinity graph of training set, where pairwise similarity is based on Euclidean distance of pollen grain silhouette
98 our patch-match based method patch exemplar selection patch match by sparse coding training stage SVM testing stage
99 discriminative patch selection
100 Exemplar Selection discriminative patch selection From a finite set of patches, V, we'd like to select M patches, which should be/have
101 Exemplar Selection discriminative patch selection From a finite set of patches, V, we'd like to select M patches, which should be/have 1. representative in feature space
102 Exemplar Selection discriminative patch selection From a finite set of patches, V, we'd like to select M patches, which should be/have 1. representative in feature space 2. spatially distributed in input space
103 Exemplar Selection discriminative patch selection From a finite set of patches, V, we'd like to select M patches, which should be/have 1. representative in feature space 2. spatially distributed in input space 3. discriminative
104 Exemplar Selection discriminative patch selection From a finite set of patches, V, we'd like to select M patches, which should be/have 1. representative in feature space 2. spatially distributed in input space 3. discriminative 4. class balance
105 Exemplar Selection discriminative patch selection From a finite set of patches, V, we'd like to select M patches, which should be/have 1. representative in feature space 2. spatially distributed in input space 3. discriminative 4. class balance 5. cluster compactness
106 Exemplar Selection discriminative patch selection From a finite set of patches, V, we'd like to select M patches, which should be/have 1. representative in feature space 2. spatially distributed in input space 3. discriminative 4. class balance 5. cluster compactness We index the selected patches by A
107 Distract a bit example: representational power Maximizing the following set function is NP-hard.
108 Distract a bit example: representational power Maximizing the following set function is NP-hard. A more general, well-known problem is the facility location problem, for example optimally placing sensors to monitor temperature. photo credited by Andreas Krause
109 selected discrminative patches Identification by patch-match sparse coding 1. Automatic patch exemplar selection (dictionary learning) based on discriminative and generative criteria
110 selected discrminative patches Identification by patch-match sparse coding 1. Automatic patch exemplar selection (dictionary learning) based on discriminative and generative criteria Automatically selected patches
111 selected discrminative patches Identification by patch-match sparse coding 1. Automatic patch exemplar selection (dictionary learning) based on discriminative and generative criteria
112 patch-match for identification Identification by patch-match sparse coding 1. Automatic patch exemplar selection (dictionary learning) 2. Spatially-aware sparse coding (SACO) - penalize dictionary elements from distant spatial locations
113 spatially aware coding (SACO) Spatial weights Test patch Exemplar patches (dictionary)
114 SACO -- Faster Matching feedforward shrinkage function by transforming dictionary patches into convolutional filters
115 SACO -- Faster Matching feedforward shrinkage function by transforming dictionary patches into convolutional filters
116 SACO -- Faster Matching feedforward shrinkage function by transforming dictionary patches into convolutional filters
117 SACO -- Faster Matching feedforward shrinkage function by transforming dictionary patches into convolutional filters
118 Quantitative Result on Fossil Pollen Represent patch using CNN feature extractor (VGG19) Global average pooling of sparse codes by SACO linear SVM Substantially outperforms standard CNN and Fisher-vector based approaches! S. Kong, S. Punyasena, C. Fowlkes, "Spatially Aware Dictionary Learning and Coding for Fossil Pollen Identification", CVPR CVMI, 2016
119 quantitative result on modern pollen We apply our approach to modern pollen grain identification. Our method Predicted Actual P. Glauca P. Mariana P. Glauca P. Mariana Surangi W Punyasena, David K Tcheng, Cassandra Wesseln, Pietra G Mueller, Classifying black and white spruce pollen using layered machine learning, New Phytologist, 2012
120 Identifying Fossil Pollen with Modern Reference Fossil pollen grains are degraded over time. using patches from modern pollen reference to identify fossilized ones modern pollen grain from glauca fossil pollen pollen grain from glauca
121 Identifying Fossil Pollen with Modern Reference Use our method to select patches from modern pollen grains Use the selected modern patches to identify fossil ones We achieve 69% accuracy wrt expert labels. modern fossil
122 Outline 1. Problem definition 2. Instantiation 3. Challenge and philosophy 4. Fine-grained classification with holistic representation 5. Fine-grained identification by matching local patches 6. Future work and conclusion
123 leaving blank Content after this page is not suitable for people to watch!
Shu Kong. Department of Computer Science, UC Irvine
Ubiquitous Fine-Grained Computer Vision Shu Kong Department of Computer Science, UC Irvine Outline 1. Problem definition 2. Instantiation 3. Challenge 4. Fine-grained classification with holistic representation
Selecting Patches, Matching Species:
Selecting Patches, Matching Species: Shu Kong CS, ICS, UCI 2016-4-6 Selecting Patches, Matching Species: Fossil Pollen Identification... Shu Kong CS, ICS, UCI 2016-4-6 Selecting Patches, Matching Species:
Hierarchical Convolutional Features for Visual Tracking
Hierarchical Convolutional Features for Visual Tracking Chao Ma Jia-Bin Huang Xiaokang Yang Ming-Husan Yang SJTU UIUC SJTU UC Merced ICCV 2015 Background Given the initial state (position and scale), estimate
Deep Networks and Beyond. Alan Yuille Bloomberg Distinguished Professor Depts. Cognitive Science and Computer Science Johns Hopkins University
Deep Networks and Beyond Alan Yuille Bloomberg Distinguished Professor Depts. Cognitive Science and Computer Science Johns Hopkins University Artificial Intelligence versus Human Intelligence Understanding
Learning Convolutional Neural Networks for Graphs
GA-65449 Learning Convolutional Neural Networks for Graphs Mathias Niepert Mohamed Ahmed Konstantin Kutzkov NEC Laboratories Europe Representation Learning for Graphs Telecom Safety Transportation Industry
Beyond R-CNN detection: Learning to Merge Contextual Attribute
Brain Unleashing Series - Beyond R-CNN detection: Learning to Merge Contextual Attribute Shu Kong CS, ICS, UCI 2015-1-29 Outline 1. RCNN is essentially doing classification, without considering contextual
Medical Image Analysis
Medical Image Analysis 1 Co-trained convolutional neural networks for automated detection of prostate cancer in multiparametric MRI, 2017, Medical Image Analysis 2 Graph-based prostate extraction in t2-weighted
Automatic Diagnosis of Ovarian Carcinomas via Sparse Multiresolution Tissue Representation
Automatic Diagnosis of Ovarian Carcinomas via Sparse Multiresolution Tissue Representation Aïcha BenTaieb, Hector Li-Chang, David Huntsman, Ghassan Hamarneh Medical Image Analysis Lab, Simon Fraser University,
CSE Introduction to High-Perfomance Deep Learning ImageNet & VGG. Jihyung Kil
CSE 5194.01 - Introduction to High-Perfomance Deep Learning ImageNet & VGG Jihyung Kil ImageNet Classification with Deep Convolutional Neural Networks Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton,
Attentional Masking for Pre-trained Deep Networks
Attentional Masking for Pre-trained Deep Networks IROS 2017 Marcus Wallenberg and Per-Erik Forssén Computer Vision Laboratory Department of Electrical Engineering Linköping University 2014 2017 Per-Erik
Mammogram Analysis: Tumor Classification
Mammogram Analysis: Tumor Classification Term Project Report Geethapriya Raghavan geeragh@mail.utexas.edu EE 381K - Multidimensional Digital Signal Processing Spring 2005 Abstract Breast cancer is the
Motivation: Attention: Focusing on specific parts of the input. Inspired by neuroscience.
Outline: Motivation. What s the attention mechanism? Soft attention vs. Hard attention. Attention in Machine translation. Attention in Image captioning. State-of-the-art. 1 Motivation: Attention: Focusing
POC Brain Tumor Segmentation. vlife Use Case
Brain Tumor Segmentation vlife Use Case 1 Automatic Brain Tumor Segmentation using CNN Background Brain tumor segmentation seeks to separate healthy tissue from tumorous regions such as the advancing tumor,
Convolutional Neural Networks (CNN)
Convolutional Neural Networks (CNN) Algorithm and Some Applications in Computer Vision Luo Hengliang Institute of Automation June 10, 2014 Luo Hengliang (Institute of Automation) Convolutional Neural Networks
Quantifying Radiographic Knee Osteoarthritis Severity using Deep Convolutional Neural Networks
Quantifying Radiographic Knee Osteoarthritis Severity using Deep Convolutional Neural Networks Joseph Antony, Kevin McGuinness, Noel E O Connor, Kieran Moran Insight Centre for Data Analytics, Dublin City
Y-Net: Joint Segmentation and Classification for Diagnosis of Breast Biopsy Images
Y-Net: Joint Segmentation and Classification for Diagnosis of Breast Biopsy Images Sachin Mehta 1, Ezgi Mercan 1, Jamen Bartlett 2, Donald Weaver 2, Joann G. Elmore 1, and Linda Shapiro 1 1 University
NMF-Density: NMF-Based Breast Density Classifier
NMF-Density: NMF-Based Breast Density Classifier Lahouari Ghouti and Abdullah H. Owaidh King Fahd University of Petroleum and Minerals - Department of Information and Computer Science. KFUPM Box 1128.
Image-Based Estimation of Real Food Size for Accurate Food Calorie Estimation
Image-Based Estimation of Real Food Size for Accurate Food Calorie Estimation Takumi Ege, Yoshikazu Ando, Ryosuke Tanno, Wataru Shimoda and Keiji Yanai Department of Informatics, The University of Electro-Communications,
Supplementary material: Backtracking ScSPM Image Classifier for Weakly Supervised Top-down Saliency
Supplementary material: Backtracking ScSPM Image Classifier for Weakly Supervised Top-down Saliency Hisham Cholakkal Jubin Johnson Deepu Rajan Nanyang Technological University Singapore {hisham002, jubin001,
Differential Attention for Visual Question Answering
Differential Attention for Visual Question Answering Badri Patro and Vinay P. Namboodiri IIT Kanpur { badri,vinaypn }@iitk.ac.in Abstract In this paper we aim to answer questions based on images when provided
GIANT: Geo-Informative Attributes for Location Recognition and Exploration
GIANT: Geo-Informative Attributes for Location Recognition and Exploration Quan Fang, Jitao Sang, Changsheng Xu Institute of Automation, Chinese Academy of Sciences October 23, 2013 Where is this? La Sagrada
Object Detectors Emerge in Deep Scene CNNs
Object Detectors Emerge in Deep Scene CNNs Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, Antonio Torralba Presented By: Collin McCarthy Goal: Understand how objects are represented in CNNs Are
Automatic Classification of Perceived Gender from Facial Images
Automatic Classification of Perceived Gender from Facial Images Joseph Lemley, Sami Abdul-Wahid, Dipayan Banik Advisor: Dr. Razvan Andonie SOURCE 2016 Outline 1 Introduction 2 Faces - Background 3 Faces
A Novel Capsule Neural Network Based Model For Drowsiness Detection Using Electroencephalography Signals
A Novel Capsule Neural Network Based Model For Drowsiness Detection Using Electroencephalography Signals Luis Guarda Bräuning (1) Nicolas Astorga (1) Enrique López Droguett (1) Marcio Moura (2) Marcelo
Mammogram Analysis: Tumor Classification
Mammogram Analysis: Tumor Classification Literature Survey Report Geethapriya Raghavan geeragh@mail.utexas.edu EE 381K - Multidimensional Digital Signal Processing Spring 2005 Abstract Breast cancer is
arxiv: v1 [stat.ml] 23 Jan 2017
![arxiv: v1 [stat.ml] 23 Jan 2017](/thumbs/81/83414183.jpg "arxiv: v1 [stat.ml] 23 Jan 2017")
Learning what to look in chest X-rays with a recurrent visual attention model arxiv:1701.06452v1 [stat.ml] 23 Jan 2017 Petros-Pavlos Ypsilantis Department of Biomedical Engineering King s College London
Convolutional Neural Networks for Text Classification
Convolutional Neural Networks for Text Classification Sebastian Sierra MindLab Research Group July 1, 2016 ebastian Sierra (MindLab Research Group) NLP Summer Class July 1, 2016 1 / 32 Outline 1 What is
IN this paper we examine the role of shape prototypes in
On the Role of Shape Prototypes in Hierarchical Models of Vision Michael D. Thomure, Melanie Mitchell, and Garrett T. Kenyon To appear in Proceedings of the International Joint Conference on Neural Networks
Learning a Discriminative Filter Bank within a CNN for Fine-grained Recognition
Learning a Discriminative Filter Bank within a CNN for Fine-grained Recognition Yaming Wang 1, Vlad I. Morariu 2, Larry S. Davis 1 1 University of Maryland, College Park 2 Adobe Research {wym, lsd}@umiacs.umd.edu
UNIVERSITY of PENNSYLVANIA CIS 520: Machine Learning Final, Fall 2014
UNIVERSITY of PENNSYLVANIA CIS 520: Machine Learning Final, Fall 2014 Exam policy: This exam allows two one-page, two-sided cheat sheets (i.e. 4 sides); No other materials. Time: 2 hours. Be sure to write
A Reliable Method for Brain Tumor Detection Using Cnn Technique
IOSR Journal of Electrical and Electronics Engineering (IOSR-JEEE) e-issn: 2278-1676,p-ISSN: 2320-3331, PP 64-68 www.iosrjournals.org A Reliable Method for Brain Tumor Detection Using Cnn Technique Neethu
HHS Public Access Author manuscript Med Image Comput Comput Assist Interv. Author manuscript; available in PMC 2018 January 04.
Discriminative Localization in CNNs for Weakly-Supervised Segmentation of Pulmonary Nodules Xinyang Feng 1, Jie Yang 1, Andrew F. Laine 1, and Elsa D. Angelini 1,2 1 Department of Biomedical Engineering,
Domain Generalization and Adaptation using Low Rank Exemplar Classifiers
Domain Generalization and Adaptation using Low Rank Exemplar Classifiers 报告人 : 李文 苏黎世联邦理工学院计算机视觉实验室 李文 苏黎世联邦理工学院 9/20/2017 1 Outline Problems Domain Adaptation and Domain Generalization Low Rank Exemplar
Action Recognition. Computer Vision Jia-Bin Huang, Virginia Tech. Many slides from D. Hoiem
Action Recognition Computer Vision Jia-Bin Huang, Virginia Tech Many slides from D. Hoiem This section: advanced topics Convolutional neural networks in vision Action recognition Vision and Language 3D
Rich feature hierarchies for accurate object detection and semantic segmentation
Rich feature hierarchies for accurate object detection and semantic segmentation Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik UC Berkeley Tech Report @ http://arxiv.org/abs/1311.2524! Detection
arxiv: v1 [cs.cv] 17 Aug 2017
![arxiv: v1 [cs.cv] 17 Aug 2017](/thumbs/78/78278805.jpg "arxiv: v1 [cs.cv] 17 Aug 2017")
Deep Learning for Medical Image Analysis Mina Rezaei, Haojin Yang, Christoph Meinel Hasso Plattner Institute, Prof.Dr.Helmert-Strae 2-3, 14482 Potsdam, Germany {mina.rezaei,haojin.yang,christoph.meinel}@hpi.de
Local Image Structures and Optic Flow Estimation
Local Image Structures and Optic Flow Estimation Sinan KALKAN 1, Dirk Calow 2, Florentin Wörgötter 1, Markus Lappe 2 and Norbert Krüger 3 1 Computational Neuroscience, Uni. of Stirling, Scotland; {sinan,worgott}@cn.stir.ac.uk
Annotation and Retrieval System Using Confabulation Model for ImageCLEF2011 Photo Annotation
Annotation and Retrieval System Using Confabulation Model for ImageCLEF2011 Photo Annotation Ryo Izawa, Naoki Motohashi, and Tomohiro Takagi Department of Computer Science Meiji University 1-1-1 Higashimita,
Multi-attention Guided Activation Propagation in CNNs
Multi-attention Guided Activation Propagation in CNNs Xiangteng He and Yuxin Peng (B) Institute of Computer Science and Technology, Peking University, Beijing, China pengyuxin@pku.edu.cn Abstract. CNNs
Towards Open Set Deep Networks: Supplemental
Towards Open Set Deep Networks: Supplemental Abhijit Bendale*, Terrance E. Boult University of Colorado at Colorado Springs {abendale,tboult}@vast.uccs.edu In this supplement, we provide we provide additional
Fine-Grained Image Classification Using Color Exemplar Classifiers
Fine-Grained Image Classification Using Color Exemplar Classifiers Chunjie Zhang 1, Wei Xiong 1, Jing Liu 2, Yifan Zhang 2, Chao Liang 3, and Qingming Huang 1,4 1 School of Computer and Control Engineering,
Object recognition and hierarchical computation
Object recognition and hierarchical computation Challenges in object recognition. Fukushima s Neocognitron View-based representations of objects Poggio s HMAX Forward and Feedback in visual hierarchy Hierarchical
Fine-Grained Image Classification Using Color Exemplar Classifiers
Fine-Grained Image Classification Using Color Exemplar Classifiers Chunjie Zhang 1, Wei Xiong 1, Jing Liu 2, Yifan Zhang 2, Chao Liang 3, Qingming Huang 1, 4 1 School of Computer and Control Engineering,
Facial Expression Classification Using Convolutional Neural Network and Support Vector Machine
Facial Expression Classification Using Convolutional Neural Network and Support Vector Machine Valfredo Pilla Jr, André Zanellato, Cristian Bortolini, Humberto R. Gamba and Gustavo Benvenutti Borba Graduate
Network Dissection: Quantifying Interpretability of Deep Visual Representation
Name: Pingchuan Ma Student number: 3526400 Date: August 19, 2018 Seminar: Explainable Machine Learning Lecturer: PD Dr. Ullrich Köthe SS 2018 Quantifying Interpretability of Deep Visual Representation
ITERATIVELY TRAINING CLASSIFIERS FOR CIRCULATING TUMOR CELL DETECTION
ITERATIVELY TRAINING CLASSIFIERS FOR CIRCULATING TUMOR CELL DETECTION Yunxiang Mao 1, Zhaozheng Yin 1, Joseph M. Schober 2 1 Missouri University of Science and Technology 2 Southern Illinois University
Putting Context into. Vision. September 15, Derek Hoiem
Putting Context into Vision Derek Hoiem September 15, 2004 Questions to Answer What is context? How is context used in human vision? How is context currently used in computer vision? Conclusions Context
Comparison of Two Approaches for Direct Food Calorie Estimation
Comparison of Two Approaches for Direct Food Calorie Estimation Takumi Ege and Keiji Yanai Department of Informatics, The University of Electro-Communications, Tokyo 1-5-1 Chofugaoka, Chofu-shi, Tokyo
Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition
Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition Charles F. Cadieu, Ha Hong, Daniel L. K. Yamins, Nicolas Pinto, Diego Ardila, Ethan A. Solomon, Najib
Algorithms in Nature. Pruning in neural networks
Algorithms in Nature Pruning in neural networks Neural network development 1. Efficient signal propagation [e.g. information processing & integration] 2. Robust to noise and failures [e.g. cell or synapse
arxiv: v2 [cs.cv] 19 Dec 2017
![arxiv: v2 [cs.cv] 19 Dec 2017](/thumbs/89/97557782.jpg "arxiv: v2 [cs.cv] 19 Dec 2017")
An Ensemble of Deep Convolutional Neural Networks for Alzheimer s Disease Detection and Classification arxiv:1712.01675v2 [cs.cv] 19 Dec 2017 Jyoti Islam Department of Computer Science Georgia State University
Bayesian Models for Combining Data Across Subjects and Studies in Predictive fmri Data Analysis
Bayesian Models for Combining Data Across Subjects and Studies in Predictive fmri Data Analysis Thesis Proposal Indrayana Rustandi April 3, 2007 Outline Motivation and Thesis Preliminary results: Hierarchical
Nature Neuroscience: doi: /nn Supplementary Figure 1. Behavioral training.
Supplementary Figure 1 Behavioral training. a, Mazes used for behavioral training. Asterisks indicate reward location. Only some example mazes are shown (for example, right choice and not left choice maze
THE human visual system has the ability to zero-in rapidly onto
1 Weakly Supervised Top-down Salient Object Detection Hisham Cholakkal, Jubin Johnson, and Deepu Rajan arxiv:1611.05345v2 [cs.cv] 17 Nov 2016 Abstract Top-down saliency models produce a probability map
DEEP CONVOLUTIONAL ACTIVATION FEATURES FOR LARGE SCALE BRAIN TUMOR HISTOPATHOLOGY IMAGE CLASSIFICATION AND SEGMENTATION
DEEP CONVOLUTIONAL ACTIVATION FEATURES FOR LARGE SCALE BRAIN TUMOR HISTOPATHOLOGY IMAGE CLASSIFICATION AND SEGMENTATION Yan Xu1,2, Zhipeng Jia2,, Yuqing Ai2,, Fang Zhang2,, Maode Lai4, Eric I-Chao Chang2
Vision: Over Ov view Alan Yuille
Vision: Overview Alan Yuille Why is Vision Hard? Complexity and Ambiguity of Images. Range of Vision Tasks. More 10x10 images 256^100 = 6.7 x 10 ^240 than the total number of images seen by all humans
Efficient Deep Model Selection
Efficient Deep Model Selection Jose Alvarez Researcher Data61, CSIRO, Australia GTC, May 9 th 2017 www.josemalvarez.net conv1 conv2 conv3 conv4 conv5 conv6 conv7 conv8 softmax prediction???????? Num Classes
Differentiating Tumor and Edema in Brain Magnetic Resonance Images Using a Convolutional Neural Network
Original Article Differentiating Tumor and Edema in Brain Magnetic Resonance Images Using a Convolutional Neural Network Aida Allahverdi 1, Siavash Akbarzadeh 1, Alireza Khorrami Moghaddam 2, Armin Allahverdy
B657: Final Project Report Holistically-Nested Edge Detection
B657: Final roject Report Holistically-Nested Edge Detection Mingze Xu & Hanfei Mei May 4, 2016 Abstract Holistically-Nested Edge Detection (HED), which is a novel edge detection method based on fully
Computational modeling of visual attention and saliency in the Smart Playroom
Computational modeling of visual attention and saliency in the Smart Playroom Andrew Jones Department of Computer Science, Brown University Abstract The two canonical modes of human visual attention bottomup
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering SUPPLEMENTARY MATERIALS 1. Implementation Details 1.1. Bottom-Up Attention Model Our bottom-up attention Faster R-CNN
Research Article Multiscale CNNs for Brain Tumor Segmentation and Diagnosis
Computational and Mathematical Methods in Medicine Volume 2016, Article ID 8356294, 7 pages http://dx.doi.org/10.1155/2016/8356294 Research Article Multiscale CNNs for Brain Tumor Segmentation and Diagnosis
DEEP LEARNING BASED VISION-TO-LANGUAGE APPLICATIONS: CAPTIONING OF PHOTO STREAMS, VIDEOS, AND ONLINE POSTS
SEOUL Oct.7, 2016 DEEP LEARNING BASED VISION-TO-LANGUAGE APPLICATIONS: CAPTIONING OF PHOTO STREAMS, VIDEOS, AND ONLINE POSTS Gunhee Kim Computer Science and Engineering Seoul National University October
Satoru Hiwa, 1 Kenya Hanawa, 2 Ryota Tamura, 2 Keisuke Hachisuka, 3 and Tomoyuki Hiroyasu Introduction
Computational Intelligence and Neuroscience Volume 216, Article ID 1841945, 9 pages http://dx.doi.org/1.1155/216/1841945 Research Article Analyzing Brain Functions by Subject Classification of Functional
CS-E Deep Learning Session 4: Convolutional Networks
CS-E4050 - Deep Learning Session 4: Convolutional Networks Jyri Kivinen Aalto University 23 September 2015 Credits: Thanks to Tapani Raiko for slides material. CS-E4050 - Deep Learning Session 4: Convolutional
Cancer Cells Detection using OTSU Threshold Algorithm
Cancer Cells Detection using OTSU Threshold Algorithm Nalluri Sunny 1 Velagapudi Ramakrishna Siddhartha Engineering College Mithinti Srikanth 2 Velagapudi Ramakrishna Siddhartha Engineering College Kodali
Visual semantics: image elements. Symbols Objects People Poses
Visible Partisanship Polmeth XXXIII, Rice University, July 22, 2016 Convolutional Neural Networks for the Analysis of Political Images L. Jason Anastasopoulos ljanastas@uga.edu (University of Georgia,
SVM-based Discriminative Accumulation Scheme for Place Recognition
SVM-based Discriminative Accumulation Scheme for Place Recognition Andrzej Pronobis CAS/CVAP, KTH Stockholm, Sweden pronobis@csc.kth.se Óscar Martínez Mozos AIS, University Of Freiburg Freiburg, Germany
Cervical cytology intelligent diagnosis based on object detection technology
Cervical cytology intelligent diagnosis based on object detection technology Meiquan Xu xumeiquan@126.com Weixiu Zeng Semptian Co., Ltd. Machine Learning Lab. zengweixiu@gmail.com Hunhui Wu 736886978@qq.com
arxiv: v1 [q-bio.nc] 12 Jun 2014
![arxiv: v1 [q-bio.nc] 12 Jun 2014](/thumbs/89/97809042.jpg "arxiv: v1 [q-bio.nc] 12 Jun 2014")
1 arxiv:1406.3284v1 [q-bio.nc] 12 Jun 2014 Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition Charles F. Cadieu 1,, Ha Hong 1,2, Daniel L. K. Yamins 1,
PMR5406 Redes Neurais e Lógica Fuzzy. Aula 5 Alguns Exemplos
PMR5406 Redes Neurais e Lógica Fuzzy Aula 5 Alguns Exemplos APPLICATIONS Two examples of real life applications of neural networks for pattern classification: RBF networks for face recognition FF networks
Representational similarity analysis
School of Psychology Representational similarity analysis Dr Ian Charest Representational similarity analysis representational dissimilarity matrices (RDMs) stimulus (e.g. images, sounds, other experimental
Chair for Computer Aided Medical Procedures (CAMP) Seminar on Deep Learning for Medical Applications. Shadi Albarqouni Christoph Baur
Chair for (CAMP) Seminar on Deep Learning for Medical Applications Shadi Albarqouni Christoph Baur Results of matching system obtained via matching.in.tum.de 108 Applicants 9 % 10 % 9 % 14 % 30 % Rank
CS231n Project: Prediction of Head and Neck Cancer Submolecular Types from Patholoy Images
CSn Project: Prediction of Head and Neck Cancer Submolecular Types from Patholoy Images Kuy Hun Koh Yoo Energy Resources Engineering Stanford University Stanford, CA 90 kohykh@stanford.edu Markus Zechner
Introduction to Machine Learning. Katherine Heller Deep Learning Summer School 2018
Introduction to Machine Learning Katherine Heller Deep Learning Summer School 2018 Outline Kinds of machine learning Linear regression Regularization Bayesian methods Logistic Regression Why we do this
arxiv: v2 [cs.cv] 22 Mar 2018
![arxiv: v2 [cs.cv] 22 Mar 2018](/thumbs/94/122062874.jpg "arxiv: v2 [cs.cv] 22 Mar 2018")
Deep saliency: What is learnt by a deep network about saliency? Sen He 1 Nicolas Pugeault 1 arxiv:1801.04261v2 [cs.cv] 22 Mar 2018 Abstract Deep convolutional neural networks have achieved impressive performance
Deep Compression and EIE: Efficient Inference Engine on Compressed Deep Neural Network
Deep Compression and EIE: Efficient Inference Engine on Deep Neural Network Song Han*, Xingyu Liu, Huizi Mao, Jing Pu, Ardavan Pedram, Mark Horowitz, Bill Dally Stanford University Our Prior Work: Deep
Classification and Statistical Analysis of Auditory FMRI Data Using Linear Discriminative Analysis and Quadratic Discriminative Analysis
International Journal of Innovative Research in Computer Science & Technology (IJIRCST) ISSN: 2347-5552, Volume-2, Issue-6, November-2014 Classification and Statistical Analysis of Auditory FMRI Data Using
Flexible, High Performance Convolutional Neural Networks for Image Classification
Flexible, High Performance Convolutional Neural Networks for Image Classification Dan C. Cireşan, Ueli Meier, Jonathan Masci, Luca M. Gambardella, Jürgen Schmidhuber IDSIA, USI and SUPSI Manno-Lugano,
arxiv: v3 [stat.ml] 28 Oct 2017
![arxiv: v3 [stat.ml] 28 Oct 2017](/thumbs/81/83820195.jpg "arxiv: v3 [stat.ml] 28 Oct 2017")
Interpretable Deep Learning applied to Plant Stress Phenotyping arxiv:1710.08619v3 [stat.ml] 28 Oct 2017 Sambuddha Ghosal sghosal@iastate.edu Asheesh K. Singh singhak@iastate.edu Arti Singh arti@iastate.edu
Data mining for Obstructive Sleep Apnea Detection. 18 October 2017 Konstantinos Nikolaidis
Data mining for Obstructive Sleep Apnea Detection 18 October 2017 Konstantinos Nikolaidis Introduction: What is Obstructive Sleep Apnea? Obstructive Sleep Apnea (OSA) is a relatively common sleep disorder
An Artificial Neural Network Architecture Based on Context Transformations in Cortical Minicolumns
An Artificial Neural Network Architecture Based on Context Transformations in Cortical Minicolumns 1. Introduction Vasily Morzhakov, Alexey Redozubov morzhakovva@gmail.com, galdrd@gmail.com Abstract Cortical
Highly Accurate Brain Stroke Diagnostic System and Generative Lesion Model. Junghwan Cho, Ph.D. CAIDE Systems, Inc. Deep Learning R&D Team
Highly Accurate Brain Stroke Diagnostic System and Generative Lesion Model Junghwan Cho, Ph.D. CAIDE Systems, Inc. Deep Learning R&D Team Established in September, 2016 at 110 Canal st. Lowell, MA 01852,
Differences of Face and Object Recognition in Utilizing Early Visual Information
Differences of Face and Object Recognition in Utilizing Early Visual Information Peter Kalocsai and Irving Biederman Department of Psychology and Computer Science University of Southern California Los
Visual Context Dan O Shea Prof. Fei Fei Li, COS 598B
Visual Context Dan O Shea Prof. Fei Fei Li, COS 598B Cortical Analysis of Visual Context Moshe Bar, Elissa Aminoff. 2003. Neuron, Volume 38, Issue 2, Pages 347 358. Visual objects in context Moshe Bar.
Automatic Quality Assessment of Cardiac MRI
Automatic Quality Assessment of Cardiac MRI Ilkay Oksuz 02.05.2018 Contact: ilkay.oksuz@kcl.ac.uk http://kclmmag.org 1 Cardiac MRI Quality Issues Need for high quality images Wide range of artefacts Manual
Automated Brain Tumor Segmentation Using Region Growing Algorithm by Extracting Feature
Automated Brain Tumor Segmentation Using Region Growing Algorithm by Extracting Feature Shraddha P. Dhumal 1, Ashwini S Gaikwad 2 1 Shraddha P. Dhumal 2 Ashwini S. Gaikwad ABSTRACT In this paper, we propose
EECS 433 Statistical Pattern Recognition
EECS 433 Statistical Pattern Recognition Ying Wu Electrical Engineering and Computer Science Northwestern University Evanston, IL 60208 http://www.eecs.northwestern.edu/~yingwu 1 / 19 Outline What is Pattern
Deep learning and non-negative matrix factorization in recognition of mammograms
Deep learning and non-negative matrix factorization in recognition of mammograms Bartosz Swiderski Faculty of Applied Informatics and Mathematics Warsaw University of Life Sciences, Warsaw, Poland bartosz_swiderski@sggw.pl
Medical Knowledge Attention Enhanced Neural Model. for Named Entity Recognition in Chinese EMR
Medical Knowledge Attention Enhanced Neural Model for Named Entity Recognition in Chinese EMR Zhichang Zhang, Yu Zhang, Tong Zhou College of Computer Science and Engineering, Northwest Normal University,
Detection of Glaucoma and Diabetic Retinopathy from Fundus Images by Bloodvessel Segmentation
International Journal of Engineering and Advanced Technology (IJEAT) ISSN: 2249 8958, Volume-5, Issue-5, June 2016 Detection of Glaucoma and Diabetic Retinopathy from Fundus Images by Bloodvessel Segmentation
Classification. Methods Course: Gene Expression Data Analysis -Day Five. Rainer Spang
Classification Methods Course: Gene Expression Data Analysis -Day Five Rainer Spang Ms. Smith DNA Chip of Ms. Smith Expression profile of Ms. Smith Ms. Smith 30.000 properties of Ms. Smith The expression
Deep Learning based Information Extraction Framework on Chinese Electronic Health Records
Deep Learning based Information Extraction Framework on Chinese Electronic Health Records Bing Tian Yong Zhang Kaixin Liu Chunxiao Xing RIIT, Beijing National Research Center for Information Science and
Modeling face recognition learning in early infant development
Modeling face recognition learning in early infant development Francesca Acerra*, Yves Burnod* and Scania de Schonen** *INSERM U483, Université Paris VI, 9 quai St Bernard, 75005 Paris, France **CNRS (LDC),
On the Use of Brainprints as Passwords
9/24/2015 2015 Global Identity Summit (GIS) 1 On the Use of Brainprints as Passwords Zhanpeng Jin Department of Electrical and Computer Engineering Department of Biomedical Engineering Binghamton University,
Towards The Deep Model: Understanding Visual Recognition Through Computational Models. Panqu Wang Dissertation Defense 03/23/2017
Towards The Deep Model: Understanding Visual Recognition Through Computational Models Panqu Wang Dissertation Defense 03/23/2017 Summary Human Visual Recognition (face, object, scene) Simulate Explain
3D Deep Learning for Multi-modal Imaging-Guided Survival Time Prediction of Brain Tumor Patients
3D Deep Learning for Multi-modal Imaging-Guided Survival Time Prediction of Brain Tumor Patients Dong Nie 1,2, Han Zhang 1, Ehsan Adeli 1, Luyan Liu 1, and Dinggang Shen 1(B) 1 Department of Radiology
Computational Cognitive Neuroscience
Computational Cognitive Neuroscience Computational Cognitive Neuroscience Computational Cognitive Neuroscience *Computer vision, *Pattern recognition, *Classification, *Picking the relevant information
CPSC81 Final Paper: Facial Expression Recognition Using CNNs
CPSC81 Final Paper: Facial Expression Recognition Using CNNs Luis Ceballos Swarthmore College, 500 College Ave., Swarthmore, PA 19081 USA Sarah Wallace Swarthmore College, 500 College Ave., Swarthmore,