Fall 2015

Location: Hoagland Hall 168
Time: Tues & Thurs 12:10pm-1:30pm
Units: 4

Instructor: Yong Jae Lee
Email: yjlee@cs  (email subject should begin with 
"[ECS 289G]")
Office: Kemper 3055
Office hours: By appointment



Announcements
  • Final project proposal due 10/22, 11:59 pm.  Please email your report in pdf format to the instructor.  See here for more details.
  • Final project report due 12/9, 11:59 pm.  Please email your report in pdf format to the instructor.  See here for more details.



Course Overview

This graduate seminar course will survey papers in a broad range of topics in computer vision, including object recognition, activity recognition, and scene understanding.  The course goals will be to understand and analyze state-of-the-art techniques, and to identify interesting open questions and future directions.  It should be of relevance to students interested in computer vision and machine learning.


Prerequisites

A course in computer vision and a course in machine learning.  Programming will be required for the final project.  Please talk to me if you are unsure if the course is a good match for your background.


Requirements

The bulk of the course will consist of student paper presentations.  Students will be responsible for writing paper reviews each week, participating in discussions, presenting once or twice in class (depending on enrollment), and completing a final project.


Grading

The final grade will be determined by:
  • Paper reviews (25%)
  • Class participation (25%)
  • Paper presentation (25%)
  • Final project (25%)
 
Important Dates
  • 10/22: Final project proposal due



Detailed course requirements and grading are here.





Schedule
 
 Date  Papers  Presenters
 9/24  Introduction   Yong Jae Lee [pdf]

 9/29  Research Overview  Yong Jae Lee [pdf]

 10/1  Image Classification

 ImageNet classification with deep convolutional neural networksA. Krizhevsky, I. Sutskever, and G. E. Hinton. NIPS 2012.
 Very Deep Convolutional Networks for Large-Scale Image Recognition. K. Simonyan and A. Zisserman. ICLR 2015.
 Mohammad [pdf]
 Maheen [pdf]
  

 10/6  Supervised Pretraining of Convolutional Neural Networks

 DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition. J. Donahue, Y. Jia, O. Vinyals, J. Hoffman, N. Zhang, E. Tzeng, and T. Darrell. ICML 2013.
 How transferable are features in deep neural networks? J. Yosinski, J. Clune, Y. Bengio, and H. Lipson. NIPS 2014.
 Philip [pdf]
 Anthony [pdf]

 10/8
 CNN basics/Caffe Tutorial
 
 Fanyi Xiao [pdf]
 Krishna Singh [pdf]

 10/13  Object Detection

 Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. R. Girshick, J. Donahue, T. Darrell, J. Malik. CVPR 2014.
 Fast R-CNN. R. Girshick. arXiv 2015.
 Muhammad [pdf]
 Charlie [pdf]

 10/15
 CNN Visualization and Analysis (I)

 Visualizing and Understanding Convolutional Networks. M. Zeiler and R. Fergus. ECCV 2014.
 Analyzing the Performance of Multilayer Neural Networks for Object Recognition. P. Agrawal, R. Girshick, J. Malik. ECCV 2014.
 Jason [pdf]
 Mohammad [pdf]

 10/20  CNN Visualization and Analysis (II)

 Understanding image representations by measuring their equivariance and equivalence. K. Lenc and A. Vedaldi. CVPR 2015. 
 Understanding Deep Image Representations by Inverting Them. A. Mahendran and A. Vedaldi. CVPR 2015.
 Yuhao [pdf]
 Anthony [pdf]

 10/22  Final project proposal due

 Fooling CNNs


 Intriguing properties of neural networks. C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. Goodfellow, R. Fergus. ICLR 2014.
 Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images. A. Nguyen, J. Yosinski, J. Clune. CVPR 2015.
 Wei-Chih [pdf]
 Charlie [pdf]

 10/27  Segmentation

 Fully Convolutional Networks for Semantic Segmentation. J. Long, E. Shelhamer, and T. Darrell. CVPR 2015.
 BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation. J. Dai, K. He, and J. Sun. ICCV 2015.
 Philipp [pdf]
 Muhammad [pdf]

 10/29  Human Pose

 Learning Human Pose Estimation Features with Convolutional Networks. A. Jain, J. Tompson, M. Andriluka, G W. Taylor and C. Bregler. ICLR 2014.
 PANDA: Pose Aligned Networks for Deep Attribute ModelingN. Zhang, M. Paluri, M. Ranzato, T. Darrell, and L. Bourdev. CVPR 2014.
 Yuhao [pdf]
 Krishna [pdf]
 

 11/3  Weakly-supervised
 

 LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop. F. Yu, Y. Zhang, S. Song, A. Seff, J. Xiao. arXiv 2015.
 
Webly Supervised Learning of Convolutional Networks. X. Chen and A. Gupta. ICCV 2015.
 Jason [pdf]
 Vicky [pdf]

 11/5  No class  

 11/10  Supervision from Spatial Context, Motion

 
Unsupervised Visual Representation Learning by Context Prediction. C. Doersch, A. Gupta, A. Efros. ICCV 2015.
 Unsupervised Learning of Spatiotemporally Coherent Metrics. R. Goroshin, J. Bruna, J. Tompson, D. Eigen, Y. LeCun. arXiv 2015.
 Maheen [pdf]
 Jackie [pdf]

 11/12  3D Scene Understanding

 Depth Map Prediction from a Single Image using a Multi-Scale Deep Network. D. Eigen, C. Puhrsch, R. Fergus. NIPS 2014.
 Designing Deep Networks for Surface Normal Estimation. X. Wang, D. Fouhey, A. Gupta. CVPR 2015.
 Wei-Chih [pdf]
 Yu-Cheng [pdf]

 11/17  Recurrent Neural Networks

 
Recurrent neural network based language model. T. Mikolov, M. Karafiat, L. Burget, J. Cernock, S. Khudanpur. Interspeech 2010.
 
Visualizing and Understanding Recurrent Networks. A. Karpathy, J. Johnson, L. Fei-Fei. arXiv 2015.
 Vicky [pdf]
 Fanyi [pdf]
 

 11/19  Language and Images
 
 Mind’s Eye: A Recurrent Visual Representation for Image Caption Generation. X. Chen and L. Zitnick. CVPR 2015.
 Final Project Discussion
 Yu-Cheng [pdf]

 11/24  Neural Network Art

 Texture synthesis and the controlled generation of natural stimuli using convolutional neural networks. L. Gatys, A. Ecker, M. Bethge. NIPS 2015.
 A Neural Algorithm of Artistic Style
L. Gatys, A. Ecker, M. Bethge. arXiv 2015.
 Yangzihao [pdf]
 Jackie [pdf]

 11/26  Thanksgiving (no class)  

 12/1  Final Project Presentations

 12/3  Final Project Presentations  





Acknowledgements

This course has been inspired by the following courses:

Subpages (1): Requirements