Presentation | 2019-10-18 [Short Paper] An attribution-based pruning method for single object detection network Rui Shi, Tianxing Li, Yasushi Yamaguchi, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Deep neural networks (DNNs) have achieved advanced results on different vision tasks. However, the cost of high computational complexity is not practical for real-time inferences running on mobile devices. In this paper, we propose an attribution-based pruning method for object detection network that reduce the computation while ensuring accuracy. First, Channel mask and spatial mask are designed to generalize attribution methods to detection networks for detecting convolution kernels that are firmly correlated with target output. Then, YOLOv3-tiny network is pruned using attribution maps and finetuned on an open-sourced mango dataset for evaluation. Compared to a state-of-the-art network trained with the same mango dataset, the experiment shows that our network achieves 83.4% computation reduction with only about 2.4% loss in accuracy. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Deep learningMango detectionNetwork pruningAttribution methods |
Paper # | PRMU2019-34 |
Date of Issue | 2019-10-11 (PRMU) |
Conference Information | |
Committee | PRMU |
---|---|
Conference Date | 2019/10/18(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Yoichi Sato(Univ. of Tokyo) |
Vice Chair | Toru Tamaki(Hiroshima Univ.) / Akisato Kimura(NTT) |
Secretary | Toru Tamaki(NTT) / Akisato Kimura(OMRON SINICX) |
Assistant | Yusuke Uchida(DeNA) / Takayoshi Yamashita(Chubu Univ.) |
Paper Information | |
Registration To | Technical Committee on Pattern Recognition and Media Understanding |
---|---|
Language | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | [Short Paper] An attribution-based pruning method for single object detection network |
Sub Title (in English) | |
Keyword(1) | Deep learningMango detectionNetwork pruningAttribution methods |
1st Author's Name | Rui Shi |
1st Author's Affiliation | The University of Tokyo(UTokyo) |
2nd Author's Name | Tianxing Li |
2nd Author's Affiliation | The University of Tokyo(UTokyo) |
3rd Author's Name | Yasushi Yamaguchi |
3rd Author's Affiliation | The University of Tokyo(UTokyo) |
Date | 2019-10-18 |
Paper # | PRMU2019-34 |
Volume (vol) | vol.119 |
Number (no) | PRMU-235 |
Page | pp.pp.17-20(PRMU), |
#Pages | 4 |
Date of Issue | 2019-10-11 (PRMU) |