Abstract | ||
---|---|---|
In this paper, we propose a simple and effective network pruning framework, which introduces novel weight-dependent gates to prune filter adaptively. We argue that the pruning decision should depend on the convolutional weights, in other words, it should be a learnable function of filter weights. We thus construct the weight-dependent gates (W-Gates) to learn the information from filter weights and obtain binary filter gates to prune or keep the filters automatically. To prune the network under hardware constraint, we train a Latency Predict Net (LPNet) to estimate the hardware latency of candidate pruned networks. Based on the proposed LPNet, we can optimize W-Gates and the pruning ratio of each layer under latency constraint. The whole framework is differentiable and can be optimized by gradient-based method to achieve a compact network with better trade-off between accuracy and efficiency. We have demonstrated the effectiveness of our method on Resnet34 and Resnet50, achieving up to 1.33/1.28 higher Top-1 accuracy with lower hardware latency on ImageNet. Compared with state-of-the-art pruning methods, our method achieves superior performance(This work is done when Yun Li, Weiqun Wu and Zechun Liu are interns at Megvii Inc (Face++)). |
Year | DOI | Venue |
---|---|---|
2020 | 10.1007/978-3-030-68238-5_3 | ECCV Workshops |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yun Li | 1 | 0 | 1.01 |
Weiqun Wu | 2 | 0 | 0.68 |
Zechun Liu | 3 | 16 | 5.27 |
C. Zhang | 4 | 90 | 12.48 |
Xiangyu Zhang | 5 | 13044 | 437.66 |
Haotian Yao | 6 | 0 | 0.34 |
Baoqun Yin | 7 | 8 | 2.83 |