Parametric Contrastive Learning

Abstract

In this paper, we propose Parametric Contrastive Learning (PaCo) to tackle long-tailed recognition. Based on theoretical analysis, we observe supervised contrastive loss tends to bias on high-frequency classes and thus increases the difficulty of imbalanced learning. We introduce a set of parametric class-wise learnable centers to rebalance from an optimization perspective. Further, we analyze our PaCo loss under a balanced setting. Our analysis demonstrates that PaCo can adaptively enhance the intensity of pushing samples of the same class close as more samples are pulled together with their corresponding centers and benefit hard example learning. Experiments on long-tailed CIFAR, ImageNet, Places, and iNaturalist 2018 manifest the new state-of-the-art for long-tailed recognition. On full ImageNet, models trained with PaCo loss surpass supervised contrastive learning across various ResNet backbones, e.g., our ResNet-200 achieves 81.8% top-1 accuracy. Our code is available at https://github.com/dvlab-research/Parametric-Contrastive-Learning.

arXiv commentICCV 2021

References in corpus (11)

• Bootstrap your own latent: A new approach to self-supervised Learning
• A systematic study of the class imbalance problem in convolutional neural networks
• Improved Regularization of Convolutional Neural Networks with Cutout
• Improved Baselines with Momentum Contrastive Learning
• Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
• DARTS: Differentiable Architecture Search
• ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
• Piecewise classifier mappings: Learning fine-grained learners for novel categories with few examples
• BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition
• Contrastive Learning with Stronger Augmentations
• ELF: An Early-Exiting Framework for Long-Tailed Classification