Paper Info
Title
Semi-supervised Active Learning for Semi-supervised Models - Exploit Adversarial Examples with Graph-based Virtual Labels.
Abstract
The performance of computer vision models significantly improves with more labeled data. However, the acquisition of labeled data is limited by the high cost. To mitigate the reliance on large labeled datasets, active learning (AL) and semi-supervised learning (SSL) are frequently adopted. Although current mainstream methods begin to combine SSL and AL (SSL-AL) to excavate the diverse expressions of unlabeled samples, these methods' fully supervised task models are still trained only with labeled data. Besides, these method's SSL-AL frameworks suffer from mismatch problems. Here, we propose a graph-based SSL-AL framework to unleash the SSL task models' power and make an effective SSL-AL interaction. In the framework, SSL leverages graph-based label propagation to deliver virtual labels to unlabeled samples, rendering AL samples' structural distribution and boosting AL. AL finds samples near the clusters' boundary to help SSL perform better label propagation by exploiting adversarial examples. The information exchange in the closed-loop realizes mutual enhancement of SSL and AL. Experimental results show that our method outperforms the state-of-the-art methods against classification and segmentation benchmarks.
Year
DOI
Venue
2021
10.1109/ICCV48922.2021.00289
ICCV
DocType
Citations 
PageRank 
Conference
0
0.34
References 
Authors
0
9
Name
Order
Citations
PageRank
Jiannan Guo100.34
Haochen Shi201.35
Yangyang Kang376.46
Kun Kuang44512.53
Siliang Tang517933.98
Zhuoren Jiang65115.18
Changlong Sun71913.89
Fei Wu82209153.88
Yue-Ting Zhuang93549216.06