Chrome Extension
WeChat Mini Program
Use on ChatGLM

Probabilistic Contrastive Learning for Long-Tailed Visual Recognition.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE(2024)

Tsinghua Univ

Cited 0|Views48
Abstract
Long-tailed distributions frequently emerge in real-world data, where a large number of minority categories contain a limited number of samples. Such imbalance issue considerably impairs the performance of standard supervised learning algorithms, which are mainly designed for balanced training sets. Recent investigations have revealed that supervised contrastive learning exhibits promising potential in alleviating the data imbalance. However, the performance of supervised contrastive learning is plagued by an inherent challenge: it necessitates sufficiently large batches of training data to construct contrastive pairs that cover all categories, yet this requirement is difficult to meet in the context of class-imbalanced data. To overcome this obstacle, we propose a novel probabilistic contrastive (ProCo) learning algorithm that estimates the data distribution of the samples from each class in the feature space, and samples contrastive pairs accordingly. In fact, estimating the distributions of all classes using features in a small batch, particularly for imbalanced data, is not feasible. Our key idea is to introduce a reasonable and simple assumption that the normalized features in contrastive learning follow a mixture of von Mises-Fisher (vMF) distributions on unit space, which brings two-fold benefits. First, the distribution parameters can be estimated using only the first sample moment, which can be efficiently computed in an online manner across different batches. Second, based on the estimated distribution, the vMF distribution allows us to sample an infinite number of contrastive pairs and derive a closed form of the expected contrastive loss for efficient optimization. Other than long-tailed problems, ProCo can be directly applied to semi-supervised learning by generating pseudo-labels for unlabeled data, which can subsequently be utilized to estimate the distribution of the samples inversely. Theoretically, we analyze the error bound of ProCo. Empirically, extensive experimental results on supervised/semi-supervised visual recognition and object detection tasks demonstrate that ProCo consistently outperforms existing methods across various datasets.
More
Translated text
Key words
Contrastive learning,long-tailed visual recognition,representation learning,semi-supervised learning,Contrastive learning,long-tailed visual recognition,representation learning,semi-supervised learning
PDF
Bibtex
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper

要点】:文章提出了一种基于概率对比学习的方法(ProCo)用于解决长尾数据在视觉识别中的问题。该方法通过估计类别样本在特征空间中的数据分布,并根据这个分布从中采样对比样本,从而克服了在不平衡数据情况下构建对比对的困难。

方法】:文章提出的ProCo方法假设对比学习中的归一化特征遵循单位空间上的一种von Mises-Fisher(vMF)分布的混合分布。通过仅使用第一样本矩来估计这个分布参数,并基于估计的分布,可以采样出无穷多个对比对,并导出对比损失的闭式形式,以实现高效优化。

实验】:文章通过在监督学习和半监督学习以及目标检测任务中对多个数据集进行广泛的实验。实验结果表明,ProCo方法在各个数据集上一致优于现有方法。