.png){kind=icon}
.png){kind=icon}
Return
Supervised Contrastive Learning With Mixed Samples for Long-Tailed Recognition
.png){kind=icon}
PRE
AI
DOI：10.1109/LSP.2025.3632235.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In the domain of signal processing and deep learning, long-tailed data distributions present significant challenges due to the class imbalance in which a few classes contain a large number of samples, while most classes have far fewer. This imbalance hinders the ability of traditional models to effectively learn from minority classes. In this work, we focus on long-tailed supervised contrastive learning and introduce a novel approach termed Mixture-based Supervised Contrastive Learning (MixSCL), which integrates image mixing techniques into the supervised contrastive learning framework. By focusing on intra-class diversity and inter-class separability, our method aims to enhance the global uniformity of feature representations and improve model robustness. Specifically, MixSCL employs dual-stream projection heads designed to optimize separately for original and mixed samples, ensuring that the introduction of mixed samples does not distort the representations of original samples. We conduct extensive evaluations on benchmark datasets including CIFAR-100-LT and ImageNet-LT, which demonstrate that MixSCL achieves superior and more balanced performance in long-tailed scenarios.
Keywords:
Long-tailed recognition
representation learning
contrastive learning
class imbalance