.png){kind=icon}
.png){kind=icon}
Return
Transfer and share: semi-supervised learning from long-tailed data
.png){kind=icon}
OA
AI
DOI：10.1007/s10994-022-06247-z.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Long-Tailed Semi-Supervised Learning (LTSSL) aims to learn from class-imbalanced data where only a few samples are annotated. Existing solutions typically require substantial cost to solve complex optimization problems, or class-balanced undersampling which can result in information loss. In this paper, we present the TRAS (TRAnsfer and Share) to effectively utilize long-tailed semi-supervised data. TRAS transforms the imbalanced pseudo-label distribution of a traditional SSL model via a delicate function to enhance the supervisory signals for minority classes. It then transfers the distribution to a target model such that the minority class will receive significant attention. Interestingly, TRAS shows that more balanced pseudo-label distribution can substantially benefit minority-class training, instead of seeking to generate accurate pseudo-labels as in previous works. To simplify the approach, TRAS merges the training of the traditional SSL model and the target model into a single procedure by sharing the feature extractor, where both classifiers help improve the representation learning. According to extensive experiments, TRAS delivers much higher accuracy than state-of-the-art methods in the entire set of classes as well as minority classes.
Keywords:
Long-tailed learning
Semi-supervised learning
Pseudo-label distribution
Logit transformation
Journal
IF:
2.9
Papers:
2.6K
Citations:
3.4W