Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification
Peng Wang1Kai Han2Xiu-Shen Wei3Lei Zhang4Lei Wang1
1University of Wollongong   2University of Bristol   3Nanjing University of Science and Technology   4Northwestern Polytechnical University

Paper [PDF]    Code [coming soon]


Learning discriminative image representations plays a vital role in long-tailed image classification because it can ease the classifier learning in imbalanced cases. Given the promising performance contrastive learning has shown recently in representation learning, in this work, we explore effective supervised contrastive learning strategies and tailor them to learn better image representations from imbalanced data in order to boost the classification accuracy thereon. Specifically, we propose a novel hybrid network structure being composed of a supervised contrastive loss to learn image representations and a cross-entropy loss to learn classifiers, where the learning is progressively transited from feature learning to the classifier learning to embody the idea that better features make better classifiers. We explore two variants of contrastive loss for feature learning, which vary in the forms but share a common idea of pulling the samples from the same class together in the normalized embedding space and pushing the samples from different classes apart. One of them is the recently proposed supervised contrastive (SC) loss, which is designed on top of the state-of-the-art unsupervised contrastive loss by incorporating positive samples from the same class. The other is a prototypical supervised contrastive (PSC) learning strategy which addresses the intensive memory consumption in standard SC loss and thus shows more promise under limited memory budget. Extensive experiments on three long-tailed classification datasets demonstrate the advantage of the proposed contrastive learning based hybrid networks in long-tailed classification.


  author    = {Peng Wang and Kai Han and Xiu-Shen Wei and Lei Zhang and Lei Wang},
  title     = {Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year      = {2021},

Webpage template was originally made by Phillip Isola and Richard Zhang for a colorful ECCV project; the code can be found here.