30/11/2020

DiscFace: Minimum Discrepancy Learning for Deep Face Recognition

Insoo Kim, Seungju Han, Seong-Jin Park, Ji-won Baek, Jinwoo Shin, Jae-Joon Han, Changkyu Choi

Keywords:

Abstract Paper Similar Papers

Abstract: Softmax-based learning methods have shown state-of-the-art performances on large-scale face recognition tasks. In this paper, we discover an important issue of softmax-based approaches: the sample features around the corresponding class weight are similarly penalized in the training phase even though their directions are different from each other. This directional discrepancy, i.e., process discrepancy leads to performance degradation at the evaluation phase. To mitigate the issue, we propose a novel training scheme, called minimum discrepancy learning that enforces directions of intra-class sample features to be aligned toward an optimal direction by using a single learnable basis. Furthermore, the single learnable basis facilitates disentangling the so-called class-invariant vectors from sample features, such that they are effective to train under class-imbalanced datasets.

The video of this talk cannot be embedded. You can watch it here:
https://accv2020.github.io/miniconf/poster_356.html
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at ACCV 2020 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
 3:26 
 0
 0
 0
 0
 2:22 
 0
 0
 0
 0
 10:39 
 0
 0
 0
 0
 2:47 
 0
 0
 0
 0
 8:28 
 0
 0
 0
 0
 7:18 
 0
 0
 0
 0
 9:06 
 0
 0
 0
 0
 15:48 
 0
 0
 0
 0
 14:31 
 0
 0
 0
 0
 13:31 
 0
 0
 0
 0
 17:04 
 1
 0
 0
 0
 5:08 
 0
 0
 0
 0
 2:49 
 0
 0
 0
 0
 4:15 
 0
 0
 0
 0
 11:57 
 0
 0
 0
 0
 3:02 
 0
 0
 0
 0
 5:18 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 11:15 
 0
 0
 0
 0
 11:27 
 0
 0
 0
 0
 18:14 
 0
 0
 0
 0
 5:10 
 0
 0
 0
 0
 14:37 
 0
 0
 0
 0
 1:04 
 0
 0
 0
 0
 2:56 
 0
 0
 0
 0
 5:12 
 1
 1
 0
 0
 2:59 
 0
 0
 0
 0
 14:34 
 0
 0
 0
 0
 15:04 
 0
 0
 0
 0
 5:09 
 0
 0
 0
 0
 7:52 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 5:19 
 0
 0
 0
 0
 12:18 
 0
 0
 0
 0
 5:18 
 0
 0
 0
 0
 14:37 
 0
 0
 0
 0
 4:05 
 0
 0
 0
 1
 5:13 
 0
 0
 0
 0
 5:19 
 0
 0
 0
 0
 5:18