papers AI Learner
The Github is limit! Click to go to the new site.

Depthwise Convolution is All You Need for Learning Multiple Visual Domains

2019-02-03
Yunhui Guo, Yandong Li, Rogerio Feris, Liqiang Wang, Tajana Rosing

Abstract

There is a growing interest in designing models that can deal with images from different visual domains. If there exists a universal structure in different visual domains that can be captured via a common parameterization, then we can use a single model for all domains rather than one model per domain. A model aware of the relationships between different domains can also be trained to work on new domains with less resources. However, to identify the reusable structure in a model is not easy. In this paper, we propose a multi-domain learning architecture based on depthwise separable convolution. The proposed approach is based on the assumption that images from different domains share cross-channel correlations but have domain-specific spatial correlations. The proposed model is compact and has minimal overhead when being applied to new domains. Additionally, we introduce a gating mechanism to promote soft sharing between different domains. We evaluate our approach on Visual Decathlon Challenge, a benchmark for testing the ability of multi-domain models. The experiments show that our approach can achieve the highest score while only requiring 50% of the parameters compared with the state-of-the-art approaches.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1902.00927

PDF

http://arxiv.org/pdf/1902.00927


Similar Posts

Comments