02/02/2021

SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data

Shaoli Huang, Xinchao Wang, Dacheng Tao

Keywords:

Abstract Paper Similar Papers

Abstract: Data mixing augmentation has proved effective in training deep models. Recent methods mix labels mainly according to the mixture proportion of image pixels. Due to the major discriminative information of a fine-grained image usually resides in subtle regions, these methods tend to introduce heavy label noise in fine-grained recognition. We propose Semantically Proportional Mixing (SnapMix) that exploits class activation map (CAM) to lessen the label noise in augmenting fine-grained data. SnapMix generates the target label for a mixed image by estimating its intrinsic semantic composition. This strategy can adapt to asymmetric mixing operations and ensure semantic correspondence between synthetic images and target labels. Experiments show that our method consistently outperforms existing mixed-based approaches regardless of different datasets or network depths. Further, by incorporating the mid-level features, the proposed SnapMix achieves top-level performance, demonstrating its potential to serve as a strong baseline for fine-grained recognition.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38947912
(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
 4:18 
 0
 0
 0
 0
 14:48 
 0
 0
 0
 0
 4:43 
 0
 0
 0
 0
 7:38 
 0
 0
 0
 0
 6:40 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 4:56 
 0
 0
 0
 0
 2:19 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 3:04 
 0
 0
 0
 0
 4:39 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 5:43 
 0
 0
 0
 0
 15:15 
 0
 0
 0
 0
 10:10 
 0
 0
 0
 0
 6:40 
 0
 0
 0
 0
 13:38 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 4:56 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 4:54 
 0
 0
 0
 0
 6:49 
 0
 0
 0
 0
 5:45 
 0
 0
 0
 0
 12:27 
 0
 0
 0
 0
 9:22 
 0
 0
 0
 0
 3:13 
 0
 0
 0
 0
 15:15 
 0
 0
 0
 0
 9:58 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 14:17 
 0
 0
 0
 1
 3:23 
 0
 0
 0
 0
 11:40 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 18:45 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 7:33 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 5:18 
 0
 0
 0
 0
 0:57