Improving Tail-Class Representation with Centroid Contrastive Learning
This addresses the challenge of class imbalance in vision tasks, offering a method to enhance tail-class performance, though it is incremental as it builds on existing decoupling approaches.
The paper tackles the problem of learning good representations for tail classes in long-tailed image datasets by proposing interpolative centroid contrastive learning (ICCL), which improves accuracy by 2.8% on the iNaturalist 2018 benchmark.
In vision domain, large-scale natural datasets typically exhibit long-tailed distribution which has large class imbalance between head and tail classes. This distribution poses difficulty in learning good representations for tail classes. Recent developments have shown good long-tailed model can be learnt by decoupling the training into representation learning and classifier balancing. However, these works pay insufficient consideration on the long-tailed effect on representation learning. In this work, we propose interpolative centroid contrastive learning (ICCL) to improve long-tailed representation learning. ICCL interpolates two images from a class-agnostic sampler and a class-aware sampler, and trains the model such that the representation of the interpolative image can be used to retrieve the centroids for both source classes. We demonstrate the effectiveness of our approach on multiple long-tailed image classification benchmarks. Our result shows a significant accuracy gain of 2.8% on the iNaturalist 2018 dataset with a real-world long-tailed distribution.