Abstract | ||
---|---|---|
Practically, person re-identification (re-ID) may suffer from the critical spatial misalignment problem due to inaccurate human detection, variation on human pose and camera viewpoint, etc. To address this, a hierarchical discriminative spatial aggregation method is proposed. The key idea is to conduct spatial aggregation on local human parts via global average-pooling to acquire the strong spatial misalignment tolerance, with VALD encoding on the local parts for facilitating discriminative power jointly. This proposition is built on NetVLAD to ensure end-to-end deep learning capacity. Due to the fine-grained property of person re-ID task that has not been well concerned by the original NetVLAD model for scene recognition, a feature refinement layer that consists of 1 fully-connected (FC) layer and 2 batch normalization (BN) layers is added on top of the raw NetVLAD layer to enhance the discriminative power and training convergence. And, a human body occlusion and background component dropout manner is also proposed to resist the effect of serious occlusion. Technically, a refined codeword initialization manner is proposed to alleviate the potential codeword imbalance problem caused by naive random initialization. The proposed discriminative spatial aggregation approach is then conducted on multi-resolution convolutional feature map layers hierarchically via early feature fusion, to involve richer semantic and fine-grained visual clues jointly. Wide-range experiments on 6 datasets (i.e., CUHK03, DukeMTMC-reID, Occluded-DukeMTMC, Market-1501, MSMT17 and Occluded-REID) verifies the effectiveness of our proposition. The source code and supporting material is available at
<uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/zmyme/HDSA-reID</uri>
. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/TIFS.2022.3146773 | IEEE Transactions on Information Forensics and Security |
Keywords | DocType | Volume |
Person re-ID,hierarchical spatial aggregation,NetVLAD,codeword imbalance problem,human body occlusion | Journal | 17 |
ISSN | Citations | PageRank |
1556-6013 | 0 | 0.34 |
References | Authors | |
26 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mingyang Zhang | 1 | 0 | 0.34 |
Yang Xiao | 2 | 237 | 26.58 |
Fu Xiong | 3 | 0 | 0.34 |
Shuai Li | 4 | 0 | 0.34 |
Zhiguo Cao | 5 | 314 | 44.17 |
Zhiwen Fang | 6 | 74 | 6.48 |
Joey Tianyi Zhou | 7 | 354 | 38.60 |