30/11/2020

Addressing Class Imbalance in Scene Graph Parsing by Learning to Contrast and Score

He Huang, Shunta Saito, Yuta Kikuchi, Eiichi Matsumoto, Wei Tang, Philip S. Yu

Keywords:

Abstract Paper Similar Papers

Abstract: Scene graph parsing aims to detect objects in an image scene and recognize their relations. Recent approaches have achieved high average scores on some popular benchmarks, but fail in detecting rare relations, as the highly long-tailed distribution of data biases the learning towards frequent labels. Motivated by the fact that detecting these rare relations can be critical in real-world applications, this paper introduces a novel integrated framework of classification and ranking to resolve the class imbalance problem in scene graph parsing. Specifically, we design a new Contrasting Cross-Entropy loss, which promotes the detection of rare relations by suppressing incorrect frequent ones. Furthermore, we propose a novel scoring module, termed as Scorer, which learns to rank the relations based on the image features and relation features to improve the recall of predictions. Our framework is simple and effective, and can be incorporated into current scene graph models. Experimental results show that the proposed approach improves the current state-of-the-art methods, with a clear advantage of detecting rare relations.

The video of this talk cannot be embedded. You can watch it here:
https://accv2020.github.io/miniconf/poster_568.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
 10:04 
 0
 0
 0
 0
 12:51 
 0
 0
 0
 0
 15:08 
 0
 0
 0
 0
 0:59 
 0
 0
 0
 0
 3:00 
 0
 0
 0
 0
 11:20 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 15:07 
 0
 0
 0
 0
 8:07 
 0
 0
 0
 0
 13:20 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 16:37 
 0
 0
 0
 0
 8:33 
 0
 0
 0
 0
 14:35 
 0
 0
 0
 0
 6:09 
 0
 0
 0
 0
 3:09 
 0
 0
 0
 0
 15:01 
 0
 0
 0
 0
 8:42 
 0
 0
 0
 0
 4:26 
 0
 0
 0
 0
 15:05 
 0
 0
 0
 0
 14:56 
 0
 0
 0
 0
 6:31 
 0
 0
 0
 0
 7:46 
 0
 0
 0
 0
 15:26 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 18:53 
 0
 1
 0
 0
 3:31 
 0
 0
 0
 0
 6:58 
 0
 0
 0
 0
 3:07 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 4:40 
 0
 0
 0
 0
 3:09 
 0
 0
 0
 0
 4:45 
 0
 0
 0
 0
 7:05 
 0
 0
 0
 0
 14:46 
 0
 0
 0
 0
 4:47 
 0
 0
 0
 0
 14:12 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 3:02 
 0
 0
 0
 0
 13:27