期刊
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
卷 -, 期 -, 页码 2824-2833出版社
IEEE COMPUTER SOC
DOI: 10.1109/CVPR.2019.00294
关键词
-
资金
- National Key Research and Development Program [2016YFB 1200203]
- National Natural Science Foundation of China [61572428, U1509206]
- Fundamental Research Funds for the Central Universities [2017FZA5014]
- Key Research and Development Program of Zhejiang Province [2018C01004]
- Startup Funding of Stevens Institute of Technology
In this paper, we investigate a novel deep-model reusing task. Our goal is to train a lightweight and versatile student model, without human-labelled annotations, that amalgamates the knowledge and masters the expertise of two pre-trained teacher models working on heterogeneous problems, one on scene parsing and the other on depth estimation. To this end, we propose an innovative training strategy that learns the parameters of the student intertwined with the teachers, achieved by projecting'' its amalgamated features onto each teacher's domain and computing the loss. We also introduce two options to generalize the proposed training strategy to handle three or more tasks simultaneously. The proposed scheme yields very encouraging results. As demonstrated on several benchmarks, the trained student model achieves results even superior to those of the teachers in their own expertise domains and on par with the state-of-the-art fully supervised models relying on human-labelled annotations.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据