.png){kind=icon}
.png){kind=icon}
Return
Contrastive Open-Set Active Learning-Based Sample Selection for Image Classification
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2024.3451928.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In this paper, we address a complex but practical scenario in Active Learning (AL) known as open-set AL, where the unlabeled data consists of both in-distribution (ID) and out-of-distribution (OOD) samples. Standard AL methods will fail in this scenario as OOD samples are highly likely to be regarded as uncertain samples, leading to their selection and wasting of the budget. Existing methods focus on selecting the highly likely ID samples, which tend to be easy and less informative. To this end, we introduce two criteria, namely contrastive confidence and historical divergence, which measure the possibility of being ID and the hardness of a sample, respectively. By balancing the two proposed criteria, highly informative ID samples can be selected as much as possible. Furthermore, unlike previous methods that require additional neural networks to detect the OOD samples, we propose a contrastive clustering framework that endows the classifier with the ability to identify the OOD samples and further enhances the network's representation learning. The experimental results demonstrate that the proposed method achieves state-of-the-art performance on several benchmark datasets.
Keywords:
Detectors
Training
Uncertainty
Labeling
Representation learning
Clustering methods
Standards
Image recognition
active learning
contrastive learning
Journal
IF:
13.7
Papers:
1.0W
Citations:
8.4W