02/02/2021

Agreement-Discrepancy-Selection: Active Learning with Progressive Distribution Alignment

Mengying Fu, Tianning Yuan, Fang Wan, Songcen Xu, Qixiang Ye

Keywords:

Abstract Paper Similar Papers

Abstract: In active learning, the ignorance of aligning unlabeled samples' distribution with that of labeled samples hinders the model trained upon labeled samples from selecting informative unlabeled samples. In this paper, we propose an agreement-discrepancy-selection (ADS) approach, and target at unifying distribution alignment with sample selection by introducing adversarial classifiers to the convolutional neural network (CNN). Minimizing classifiers' prediction discrepancy (maximizing prediction agreement) drives learning CNN features to reduce the distribution bias of labeled and unlabeled samples, while maximizing classifiers' discrepancy highlights informative samples. Iterative optimization of agreement and discrepancy loss calibrated with an entropy function drives aligning sample distributions in a progressive fashion for effective active learning. Experiments on image classification and object detection tasks demonstrate that ADS is task-agnostic, while significantly outperforms the previous methods when the labeled sets are small.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38947768
(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
 10:52 
 0
 0
 0
 0
 13:34 
 0
 0
 0
 0
 0:58 
 0
 0
 0
 0
 4:56 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 5:19 
 0
 0
 0
 0
 3:05 
 0
 0
 0
 0
 7:54 
 0
 0
 0
 0
 3:36 
 0
 0
 0
 0
 10:00 
 0
 0
 0
 0
 14:01 
 0
 0
 0
 0
 10:11 
 0
 0
 0
 0
 12:21 
 0
 0
 0
 0
 3:16 
 0
 0
 0
 0
 14:32 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 11:48 
 0
 0
 0
 0
 14:28 
 0
 0
 0
 0
 14:12 
 0
 0
 0
 0
 14:00 
 0
 0
 0
 0
 15:22 
 0
 0
 0
 0
 5:16 
 0
 0
 0
 0
 5:17 
 0
 0
 0
 0
 13:17 
 0
 0
 0
 0
 8:21 
 0
 0
 0
 0
 4:49 
 0
 0
 0
 0
 5:25 
 0
 0
 0
 0
 13:19 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 11:41 
 0
 0
 0
 0
 3:18 
 0
 0
 0
 0
 9:26 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 13:04 
 0
 0
 0
 0
 2:57 
 0
 0
 0
 0
 11:20 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 12:26 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 2:50