• Home
  • Search
  • Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification
  • Open Access IconOpen Access
  • Cite Icon289
  • https://doi.org/10.1109/cvpr46437.2021.00100Copy DOI Icon

Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification

  • Jun 1, 2021
  • Peng Wang +4 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

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.

Similar Papers
  • Research Article
  • Citations4

Deep learning and smart energy-based lightweight urban power load forecasting model for sustainable urban growth

  • Jan 15, 2025
  • Frontiers in Sustainable Cities
  • Haewon Byeon +5
  • Conference Article
  • Citations6

Self-Supervised Learning of Audio Representations using Angular Contrastive Loss

  • Jun 04, 2023
  • Shanshan Wang +2
  • Book Chapter

Spatial-Spectral Siamese and Similarity Network for Hyperspectral Image Classification

  • Jan 01, 2023
  • Wenyue Yu +5
  • Research Article
  • Citations2

Infrared Image Generation Based on Visual State Space and Contrastive Learning

  • Oct 14, 2024
  • Remote Sensing
  • Bing Li +5
  • Research Article
  • Citations31

Vision Transformer With Contrastive Learning for Hyperspectral Image Classification

  • Jan 01, 2023
  • IEEE Geoscience and Remote Sensing Letters
  • Heng Zhou +3
  • Conference Article
  • Citations265

Vision-Language Pre-Training with Triple Contrastive Learning

  • Jun 01, 2022
  • Jinyu Yang +8
  • Research Article

Cross-view contrastive representation learning on meta-path induced graphs with node features for bundle recommendation.

  • Jul 01, 2026
  • Neural networks : the official journal of the International Neural Network Society
  • Peng Zhang +4
  • PDF
  • Research Article
  • Citations22

SSCLNet: A Self-Supervised Contrastive Loss-Based Pre-Trained Network for Brain MRI Classification

  • Jan 01, 2023
  • IEEE Access
  • Animesh Mishra +2
  • Conference Article
  • Citations459

Representation Learning by Learning to Count

  • Oct 01, 2017
  • Mehdi Noroozi +2
  • Research Article
  • Citations8

Multiview Self-Supervised Segmentation for OARs Delineation in Radiotherapy

  • Mar 05, 2021
  • Evidence-based Complementary and Alternative Medicine : eCAM
  • Cong Liu +3
  • Research Article
  • Citations42

TSSK-Net: Weakly supervised biomarker localization and segmentation with image-level annotation in retinal OCT images

  • Dec 21, 2022
  • Computers in Biology and Medicine
  • Xiaoming Liu +4
  • Book Chapter

Self-supervised Contrastive Representation Learning for Semi-supervised Time-series Classification

  • Mar 19, 2026
  • Emadeldeen Eldele +6
  • Book Chapter
  • Citations11

Geographically Local Representation Learning with a Spatial Prior for Visual Localization

  • Jan 01, 2020
  • Zimin Xia +3
  • Research Article
  • Citations5

Attention-based hybrid contrastive learning for unsupervised person re-identification

  • Apr 17, 2025
  • Scientific Reports
  • Weihao Qin +5
  • Conference Article
  • Citations187

Self-paced Ensemble for Highly Imbalanced Massive Data Classification

  • Apr 01, 2020
  • Zhining Liu +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.