Push for Center Learning via Orthogonalization and Subspace Masking for Person Re-Identification
arXiv:1908.10535
Abstract
Person re-identification aims to identify whether pairs of images belong to the same person or not. This problem is challenging due to large differences in camera views, lighting and background. One of the mainstream in learning CNN features is to design loss functions which reinforce both the class separation and intra-class compactness. In this paper, we propose a novel Orthogonal Center Learning method with Subspace Masking for person re-identification. We make the following contributions: (i) we develop a center learning module to learn the class centers by simultaneously reducing the intra-class differences and inter-class correlations by orthogonalization; (ii) we introduce a subspace masking mechanism to enhance the generalization of the learned class centers; and (iii) we devise to integrate the average pooling and max pooling in a regularizing manner that fully exploits their powers. Extensive experiments show that our proposed method consistently outperforms the state-of-the-art methods on the large-scale ReID datasets including Market-1501, DukeMTMC-ReID, CUHK03 and MSMT17.
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- In Defense of the Triplet Loss for Person Re-Identification
- Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
- Person Re-identification: Past, Present and Future
- Improving Person Re-identification by Attribute and Identity Learning
- A Discriminatively Learned CNN Embedding for Person Re-identification
- Random Erasing Data Augmentation
- DropBlock: A regularization method for convolutional networks
- Large-Margin Softmax Loss for Convolutional Neural Networks
- On orthogonality and learning recurrent networks with long term dependencies
- Orthogonal Weight Normalization: Solution to Optimization over Multiple Dependent Stiefel Manifolds in Deep Neural Networks
- Horizontal Pyramid Matching for Person Re-identification
- Divide and Fuse: A Re-ranking Approach for Person Re-identification