2017

Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro

Zheng, Zhedong, Zheng, Liang, Yang, Yi

Understand

The main contribution of this paper is a simple semi-supervised pipeline that only uses the original training set without collecting extra data.

It is challenging in 1) how to obtain more training data only from the training set and 2) how to use the newly generated data.
In this work, the generative adversarial network (GAN) is used to generate unlabeled samples.
We propose the label smoothing regularization for outliers (LSRO).

Built on

Reducing the dimensionality of data with neural networks
G. E. Hinton and R. R. Salakhutdinov · 2006
Earlier work this paper cites.
Semi-supervised learning of compact document representations with deep networks
M. Ranzato and M. Szummer · 2008
Earlier work this paper cites.
Object detection with discriminatively trained part-based models
P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan · 2010
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.
Large scale metric learning from equivalence constraints
M. Köstinger, M. Hirzer, P. Wohlhart, P. M. Roth, and H. Bischof · 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.
Bicov: a novel image representation for person re-identification and face verification
B. Ma, Y. Su, and F. Jurie · 2012
Earlier work this paper cites.
Multi-prediction deep boltzmann machines
I. Goodfellow, M. Mirza, A. Courville, and Y. Bengio · 2013
Earlier work this paper cites.
Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks
D.-H. Lee · 2013
Earlier work this paper cites.
Generative adversarial nets
I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio · 2014
Earlier work this paper cites.
Adam: A method for stochastic optimization
Original
D. Kingma and J. Ba · 2014
Earlier work this paper cites.
Deepreid: Deep filter pairing neural network for person re-identification
W. Li, R. Zhao, T. Xiao, and X. Wang · 2014
Earlier work this paper cites.
Covariance descriptor based on bio-inspired features for person re-identification and face verification
B. Ma, Y. Su, and F. Jurie · 2014
Earlier work this paper cites.
Deep metric learning for practical person re-identification
Original
D. Yi, Z. Lei, and S. Z. Li · 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.
An improved deep learning architecture for person re-identification
E. Ahmed, M. Jones, and T. K. Marks · 2015
Earlier work this paper cites.
Person re-identification by local maximal occurrence representation and metric learning
S. Liao, Y. Hu, X. Zhu, and S. Z. Li · 2015
Earlier work this paper cites.

Similar

Weakly-and semi-supervised learning of a deep convolutional network for semantic image segmentation
G. Papandreou, L.-C. Chen, K. P. Murphy, and A. L. Yuille · 2015
Cited alongside, same era.
Semi-supervised learning with ladder networks
A. Rasmus, M. Berglund, M. Honkala, H. Valpola, and T. Raiko · 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, et al · 2015
Cited alongside, same era.
Multiregion bilinear convolutional neural networks for person re-identification
Original
E. Ustinova, Y. Ganin, and V. Lempitsky · 2015
Cited alongside, same era.
Matconvnet – convolutional neural networks for matlab
A. Vedaldi and K. Lenc · 2015
Cited alongside, same era.
Multiple granularity descriptors for fine-grained categorization
D. Wang, Z. Shen, J. Shao, W. Zhang, X. Xue, and Z. Zhang · 2015
Cited alongside, same era.
Scalable person re-identification: A benchmark
L. Zheng, L. Shen, L. Tian, S. Wang, J. Wang, and Q. Tian · 2015
Cited alongside, same era.
Tensorflow: A system for large-scale machine learning
M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S. Ghemawat, G. Irving, M. Isard, et al · 2016
Cited alongside, same era.
Similarity learning with spatial constraints for person re-identification
D. Chen, Z. Yuan, B. Chen, and N. Zheng · 2016
Cited alongside, same era.
Infogan: Interpretable representation learning by information maximizing generative adversarial nets
X. Chen, Y. Duan, R. Houthooft, J. Schulman, I. Sutskever, and P. Abbeel · 2016
Cited alongside, same era.
Person re-identification by multi-channel parts-based cnn with improved triplet loss function
D. Cheng, Y. Gong, S. Zhou, J. Wang, and N. Zheng · 2016
Cited alongside, same era.
Deep transfer learning for person re-identification
Original
M. Geng, Y. Wang, T. Xiang, and Y. Tian · 2016
Cited alongside, same era.

Then

Performance measures and a data set for multi-target, multi-camera tracking
E. Ristani, F. Solera, R. Zou, R. Cucchiara, and C. Tomasi · 2016
Later among the works it cites.
Improved techniques for training gans
T. Salimans, I. Goodfellow, W. Zaremba, V. Cheung, A. Radford, and X. Chen · 2016
Later among the works it cites.
Rethinking the inception architecture for computer vision
C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna · 2016
Later among the works it cites.
Gated siamese convolutional neural network architecture for human re-identification
R. R. Varior, M. Haloi, and G. Wang · 2016
Later among the works it cites.
A siamese long short-term memory architecture for human re-identification
R. R. Varior, B. Shuai, J. Lu, D. Xu, and G. Wang · 2016
Later among the works it cites.
Joint learning of single-image and cross-image representations for person re-identification
F. Wang, W. Zuo, L. Lin, D. Zhang, and L. Zhang · 2016
Later among the works it cites.
Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling
J. Wu, C. Zhang, T. Xue, B. Freeman, and J. Tenenbaum · 2016
Later among the works it cites.
Deep linear discriminant analysis on fisher networks: A hybrid architecture for person re-identification
L. Wu, C. Shen, and A. van den Hengel · 2016
Later among the works it cites.
An enhanced deep feature representation for person re-identification
S. Wu, Y.-C. Chen, X. Li, A.-C. Wu, J.-J. You, and W.-S. Zheng · 2016
Later among the works it cites.
End-to-end deep learning for person search
Original
T. Xiao, S. Li, B. Wang, L. Lin, and X. Wang · 2016
Later among the works it cites.
Semantic image inpainting with perceptual and contextual losses
Original
R. Yeh, C. Chen, T. Y. Lim, M. Hasegawa-Johnson, and M. N. Do · 2016
Later among the works it cites.
Learning a discriminative null space for person re-identification
Original
L. Zhang, T. Xiang, and S. Gong · 2016
Later among the works it cites.
Person re-identification: Past, present and future
Original
L. Zheng, Y. Yang, and A. G. Hauptmann · 2016
Later among the works it cites.
Person re-identification in the wild
Original
L. Zheng, H. Zhang, S. Sun, M. Chandraker, and Q. Tian · 2016
Later among the works it cites.
A discriminatively learned cnn embedding for person re-identification
Original
Z. Zheng, L. Zheng, and Y. Yang · 2016
Later among the works it cites.
Looking beyond appearances: Synthetic training data for deep cnns in re-identification
Original
I. B. Barbosa, M. Cristani, B. Caputo, A. Rognhaugen, and T. Theoharis · 2017
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…