2018

Adversarial Complementary Learning for Weakly Supervised Object Localization

Zhang, Xiaolin, Wei, Yunchao, Feng, Jiashi et al.

Understand

In this work, we propose Adversarial Complementary Learning (ACoL) to automatically localize integral objects of semantic interest with weak supervision.

We first mathematically prove that class localization maps can be obtained by directly selecting the class-specific feature maps of the last convolutional layer, which paves a simple way to identify object regions.
We then present a simple network architecture including two parallel-classifiers for object localization.
Specifically, we leverage one classification branch to dynamically localize some discriminative object regions during the forward pass.

Built on

Caltech-256 object category dataset
G. Griffin, A. Holub, and P. Perona · 2007
Earlier work this paper cites.
Imagenet: A large-scale hierarchical image database
J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei · 2009
Earlier work this paper cites.
The Caltech-UCSD Birds-200-2011 Dataset
C. Wah, S. Branson, P. Welinder, P. Perona, and S. Belongie · 2011
Earlier work this paper cites.
Weakly supervised localization and learning with generic knowledge
T. Deselaers, B. Alexe, and V. Ferrari · 2012
Earlier work this paper cites.
Imagenet classification with deep convolutional neural networks
A. Krizhevsky, I. Sutskever, and G. E. Hinton · 2012
Earlier work this paper cites.
Network in network
M. Lin, Q. Chen, and S. Yan · 2013
Earlier work this paper cites.
Deep inside convolutional networks: Visualising image classification models and saliency maps
Original
K. Simonyan, A. Vedaldi, and A. Zisserman · 2013
Earlier work this paper cites.
Deformable part descriptors for fine-grained recognition and attribute prediction
N. Zhang, R. Farrell, F. Iandola, and T. Darrell · 2013
Earlier work this paper cites.
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 · 2014
Earlier work this paper cites.
Rich feature hierarchies for accurate object detection and semantic segmentation
R. Girshick, J. Donahue, T. Darrell, and J. Malik · 2014
Earlier work this paper cites.
Overfeat: Integrated recognition, localization and detection using convolutional networks
P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, R. Fergus, and Y. LeCun · 2014
Earlier work this paper cites.
Going deeper with convolutions
Original
C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich · 2014
Earlier work this paper cites.
Video object discovery and co-segmentation with extremely weak supervision
L. Wang, G. Hua, R. Sukthankar, J. Xue, and N. Zheng · 2014
Earlier work this paper cites.
Visualizing and understanding convolutional networks
M. D. Zeiler and R. Fergus · 2014
Earlier work this paper cites.
Part-based r-cnns for fine-grained category detection
N. Zhang, J. Donahue, R. Girshick, and T. Darrell · 2014
Earlier work this paper cites.
Look and think twice: Capturing top-down visual attention with feedback convolutional neural networks
C. Cao, X. Liu, Y. Yang, Y. Yu, J. Wang, Z. Wang, Y. Huang, L. Wang, C. Huang, W. Xu, et al · 2015
Earlier work this paper cites.

Similar

Local alignments for fine-grained categorization
E. Gavves, B. Fernando, C. G. Snoek, A. W. Smeulders, and T. Tuytelaars · 2015
Cited alongside, same era.
Fast r-cnn
Original
R. Girshick · 2015
Cited alongside, same era.
Towards computational baby learning: A weakly-supervised approach for object detection
X. Liang, S. Liu, Y. Wei, L. Liu, L. Lin, and S. Yan · 2015
Cited alongside, same era.
Is object localization for free?-weakly-supervised learning with convolutional neural networks
M. Oquab, L. Bottou, I. Laptev, and J. Sivic · 2015
Cited alongside, same era.
Weakly-and semi-supervised learning of a dcnn for semantic image segmentation
Original
G. Papandreou, L.-C. Chen, K. Murphy, and A. L. Yuille · 2015
Cited alongside, same era.
Faster r-cnn: Towards real-time object detection with region proposal networks
S. Ren, K. He, R. Girshick, and J. Sun · 2015
Cited alongside, same era.
ImageNet Large Scale Visual Recognition Challenge
O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and L. Fei-Fei · 2015
Cited alongside, same era.
Very deep convolutional networks for large-scale image recognition
K. Simonyan and A. Zisserman · 2015
Cited alongside, same era.
Self-taught object localization with deep networks
L. Bazzani, A. Bergamo, D. Anguelov, and L. Torresani · 2016
Cited alongside, same era.
Weakly supervised localization using deep feature maps
A. J. Bency, H. Kwon, H. Lee, S. Karthikeyan, and B. Manjunath · 2016
Cited alongside, same era.
Deep residual learning for image recognition
K. He, X. Zhang, S. Ren, and J. Sun · 2016
Cited alongside, same era.
Bottom-up top-down cues for weakly-supervised semantic segmentation
Original
Q. Hou, P. K. Dokania, D. Massiceti, Y. Wei, M.-M. Cheng, and P. Torr · 2016
Cited alongside, same era.

Then

What’s the point: Semantic segmentation with point supervision
O. Russakovsky, A. Bearman, V. Ferrari, and L. Fei-Fei · 2016
Later among the works it cites.
Learning to segment with image-level annotations
Y. Wei, X. Liang, Y. n. Chen, Z. Jie, Y. Xiao, Y. Zhao, and S. Yan · 2016
Later among the works it cites.
Hcp: A flexible cnn framework for multi-label image classification
Y. Wei, W. Xia, M. Lin, J. Huang, B. Ni, J. Dong, Y. Zhao, and S. Yan · 2016
Later among the works it cites.
Top-down neural attention by excitation backprop
J. Zhang, Z. Lin, J. Brandt, X. Shen, and S. Sclaroff · 2016
Later among the works it cites.
Learning Deep Features for Discriminative Localization
B. Zhou, A. Khosla, L. A., A. Oliva, and A. Torralba · 2016
Later among the works it cites.
Discovering class-specific pixels for weakly-supervised semantic segmentation
Original
A. Chaudhry, P. K. Dokania, and P. H. Torr · 2017
Later among the works it cites.
Dual path networks
Original
Y. Chen, J. Li, H. Xiao, X. Jin, S. Yan, and J. Feng · 2017
Later among the works it cites.
A dual-network progressive approach to weakly supervised object detection
X. Dong, D. Meng, F. Ma, and Y. Yang · 2017
Later among the works it cites.
Few-example object detection with model communication
Original
X. Dong, L. Zheng, F. Ma, Y. Yang, and D. Meng · 2017
Later among the works it cites.
Deep self-taught learning for weakly supervised object localization
Z. Jie, Y. Wei, X. Jin, and J. Feng · 2017
Later among the works it cites.
Two-phase learning for weakly supervised object localization
Original
D. Kim, D. Yoo, I. S. Kweon, et al · 2017
Later among the works it cites.
Feature pyramid networks for object detection
T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie · 2017
Later among the works it cites.
Hide-and-seek: Forcing a network to be meticulous for weakly-supervised object and action localization
Original
K. K. Singh and Y. J. Lee · 2017
Later among the works it cites.
Object region mining with adversarial erasing: A simple classification to semantic segmentation approach
Y. Wei, J. Feng, X. Liang, C. Ming-Ming, Y. Zhao, and S. Yan · 2017
Later among the works it cites.
Stc: A simple to complex framework for weakly-supervised semantic segmentation
Y. Wei, X. Liang, Y. Chen, X. Shen, M.-M. Cheng, J. Feng, Y. Zhao, and S. Yan · 2017
Later among the works it cites.
Revisiting dilated convolution: A simple approach for weakly- and semi- supervised semantic segmentation
Y. Wei, H. Xiao, H. Shi, Z. Jie, J. Feng, and T. S. Huang · 2018
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…