Push for Center Learning via Orthogonalization and Subspace Masking for Person Re-Identification
This work addresses the challenge of identifying individuals across different camera views in surveillance, representing an incremental improvement in feature learning for person re-identification.
The paper tackles person re-identification by proposing an orthogonal center learning method with subspace masking to reduce intra-class differences and inter-class correlations, achieving state-of-the-art performance on large-scale datasets like Market-1501 and DukeMTMC-ReID.
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.