.png){kind=icon}
返回
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}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
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.
Keyword:
Long-tailed learning
Semi-supervised learning
Pseudo-label distribution
Logit transformation
期刊
IF:
2.9
论文数:
2.7K
被引数:
3.4W
机构
引用论文
Movements of frugivorous birds among fragmented rainforests in the Northern Territory, Australia
PREAI
分享收藏Hybrid ferroelectric–polymer microfluidic device for dielectrophoretic self-assembling of nanoparticles.png)
RSC Adv.
RSC Adv.IF0
PREAI
分享收藏
分享收藏Developing Wind and/or Solar Powered Crop Irrigation Systems for the Great Plains为大平原开发风能和/或太阳能作物灌溉系统
PREAI
分享收藏
查看更多内容