02/02/2021

Exploiting Diverse Characteristics and Adversarial Ambivalence for Domain Adaptive Segmentation

Bowen Cai, Huan Fu, Rongfei Jia, Binqiang Zhao, Hua Li, Yinghui Xu

Keywords:

Abstract Paper Similar Papers

Abstract: Adapting semantic segmentation models to new domains is an important but challenging problem. Recently enlightening progress has been made, but the performance of existing methods is unsatisfactory on real datasets where the new target domain comprises of heterogeneous sub-domains (e.g. diverse weather characteristics). We point out that carefully reasoning about the multiple modalities in the target domain can improve the robustness of adaptation models. To this end, we propose a condition-guided adaptation framework that is empowered by a special attentive progressive adversarial training (APAT) mechanism and a novel self-training policy. The APAT strategy progressively performs condition-specific alignment and attentive global feature matching. The new self-training scheme exploits the adversarial ambivalences of easy and hard adaptation regions and the correlations among target sub-domains effectively. We evaluate our method (DCAA) on various adaptation scenarios where the target images vary in weather conditions. The comparisons against baselines and the state-of-the-art approaches demonstrate the superiority of DCAA over the competitors.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948340
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 19:41 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 5:07 
 0
 0
 0
 0
 5:10 
 0
 0
 0
 0
 13:20 
 0
 0
 0
 0
 8:57 
 0
 0
 0
 0
 10:58 
 0
 0
 0
 0
 7:09 
 0
 0
 0
 0
 2:56 
 2
 0
 0
 0
 9:31 
 0
 0
 0
 0
 14:40 
 0
 0
 0
 1
 9:03 
 0
 0
 0
 0
 4:52 
 0
 0
 0
 0
 14:41 
 0
 0
 0
 0
 15:01 
 0
 0
 0
 0
 5:45 
 0
 0
 0
 0
 6:32 
 0
 0
 0
 0
 14:52 
 0
 0
 0
 0
 7:53 
 0
 0
 0
 0
 14:11 
 0
 0
 0
 0
 7:17 
 0
 0
 0
 0
 12:41 
 0
 0
 0
 0
 13:21 
 0
 0
 0
 0
 7:28 
 0
 0
 0
 0
 20:50 
 0
 0
 0
 0
 15:33 
 0
 0
 0
 0
 3:23 
 0
 1
 0
 0
 15:01 
 0
 0
 0
 0
 14:34 
 0
 0
 0
 0
 13:26 
 0
 0
 0
 0
 8:59 
 0
 0
 0
 0
 4:57 
 0
 0
 0
 0
 11:33 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 10:55 
 0
 0
 0
 0
 3:16 
 0
 0
 0
 0
 1:33 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 1:00