.png){kind=icon}
.png){kind=icon}
Return
Improving Tail-Class Representation with Centroid Contrastive Learning
.png){kind=icon}
OA
AI
DOI：10.1016/j.patrec.2023.03.010.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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 rep-resentations 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 in-terpolates 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 classifi-cation benchmarks. (c) 2023 Elsevier B.V. All rights reserved.
Keywords:
Long-tailed classification
Imbalanced learning
Contrastive learning
Deep learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.3
Papers:
7.8K
Citations:
1.6W