Name
Abstract | ||
|---|---|---|
Deep learning has shown significant successes in person reidentification (re-id) tasks. However, most existing works focus on discriminative feature learning and impose complex neural networks, suffering from low inference efficiency. In fact, feature extraction time is also crucial for real-world applications and lightweight models are needed. Prevailing pruning methods usually pay attention to compact classification models. However, these methods are suboptimal for compacting re-id models, which usually produce continuous features and are sensitive to network pruning. The key point of pruning re-id models is how to retain the original filter distribution in continuous features as much as possible. In this work, we propose a blockwise adjacent filter decaying method to fill this gap. Specifically, given a trained model, we first evaluate the redundancy of filters based on the adjacency relationships to preserve the original filter distribution. Second, previous layerwise pruning methods ignore that discriminative information is enhanced block-by-block. Therefore, we propose a blockwise filter pruning strategy to better utilize the block relations in the pretrained model. Third, we propose a novel filter decaying policy to progressively reduce the scale of redundant filters. Different from conventional soft filter pruning that directly sets the filter values as zeros, the proposed filter decaying can keep the pretrained knowledge as much as possible. We evaluate our method on three popular person reidentification datasets, that is: 1) Market-1501; 2) DukeMTMC-reID; and 3) MSMT17_V1. The proposed method shows superior performance to the existing state-of-the-art pruning methods. After pruning over 91.9% parameters on DukeMTMC-reID, the Rank-1 accuracy only drops 3.7%, demonstrating its effectiveness for compacting person reidentification. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1109/TCYB.2021.3130047 | IEEE Transactions on Cybernetics |
Keywords | DocType | Volume |
Humans,Neural Networks, Computer | Journal | 52 |
Issue | ISSN | Citations |
12 | 2168-2267 | 0 |
PageRank | References | Authors |
0.34 | 23 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xiaodong Wang | 1 | 35 | 5.19 |
| Zhedong Zheng | 2 | 366 | 19.63 |
| Yang He | 3 | 61 | 4.14 |
| Fei Yan | 4 | 28 | 9.01 |
| Zhiqiang Zeng | 5 | 139 | 16.35 |
| Yi Yang | 6 | 6873 | 271.72 |