Abstract | ||
---|---|---|
This paper aims at addressing the problem of substantial performance degradation at extremely low computational cost (e.g. 5M FLOPs on ImageNet classification). We found that two factors, sparse connectivity and dynamic activation function, are effective to improve the accuracy. The former avoids the significant reduction of network width, while the latter mitigates the detriment of reduction in n... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ICCV48922.2021.00052 | 2021 IEEE/CVF International Conference on Computer Vision (ICCV) |
Keywords | DocType | ISBN |
Image recognition,Convolution,Pose estimation,Object detection,Performance gain,Solids,Computational efficiency | Conference | 978-1-6654-2812-5 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
9 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yunsheng Li | 1 | 33 | 3.77 |
Yinpeng Chen | 2 | 186 | 23.77 |
Xiyang Dai | 3 | 25 | 6.88 |
Dongdong Chen | 4 | 52 | 19.10 |
Mengchen Liu | 5 | 426 | 16.26 |
Lu Yuan | 6 | 0 | 0.68 |
zicheng liu | 7 | 3662 | 199.64 |
Lei Zhang | 8 | 0 | 0.34 |
Nuno Vasconcelos | 9 | 5410 | 273.99 |