Dataset Awareness is not Enough: Implementing Sample-level Tail Encouragement in Long-tailed Self-supervised Learning
This work addresses the problem of long-tailed recognition in self-supervised learning for real-world applications, representing an incremental improvement over existing methods.
The paper tackles performance degradation in self-supervised learning on long-tailed datasets by proposing TASE, a method that uses pseudo-labels to dynamically adjust temperature and re-weighting at the sample level, achieving outstanding performance and high robustness across six benchmarks on three datasets.
Self-supervised learning (SSL) has shown remarkable data representation capabilities across a wide range of datasets. However, when applied to real-world datasets with long-tailed distributions, performance on multiple downstream tasks degrades significantly. Recently, the community has begun to focus more on self-supervised long-tailed learning. Some works attempt to transfer temperature mechanisms to self-supervised learning or use category-space uniformity constraints to balance the representation of different categories in the embedding space to fight against long-tail distributions. However, most of these approaches focus on the joint optimization of all samples in the dataset or on constraining the category distribution, with little attention given to whether each individual sample is optimally guided during training. To address this issue, we propose Temperature Auxiliary Sample-level Encouragement (TASE). We introduce pseudo-labels into self-supervised long-tailed learning, utilizing pseudo-label information to drive a dynamic temperature and re-weighting strategy. Specifically, We assign an optimal temperature parameter to each sample. Additionally, we analyze the lack of quantity awareness in the temperature parameter and use re-weighting to compensate for this deficiency, thereby achieving optimal training patterns at the sample level. Comprehensive experimental results on six benchmarks across three datasets demonstrate that our method achieves outstanding performance in improving long-tail recognition, while also exhibiting high robustness.