paper-with-me

Papers

Supervised Contrastive Learning on Blended Images for Long-tailed Recognition

2022-11-22 · Minki Jeong, Changick Kim

Real-world data often have a long-tailed distribution, where the number of samples per class is not equal over training classes. The imbalanced data form a biased feature space, which deteriorates the performance of the recognition model. In this paper, we propose a novel long-tailed recognition method to balance the latent feature space. First, we introduce a MixUp-based data augmentation technique to reduce the bias of the long-tailed data. Furthermore, we propose a new supervised contrastive learning method, named Supervised contrastive learning on Mixed Classes (SMC), for blended images. SMC creates a set of positives based on the class labels of the original images. The combination ratio of positives weights the positives in the training loss. SMC with the class-mixture-based loss explores more diverse data space, enhancing the generalization capability of the model. Extensive experiments on various benchmarks show the effectiveness of our one-stage training method.

📄 PDF Abstract BibTeX arXiv:2211.11938

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningData AugmentationLong-tail Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification

2021-03-26 · CVPR 2021 1 · Peng Wang, Kai Han, Xiu-Shen Wei, Lei Zhang 외

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 h…

ClassificationContrastive LearningGeneral Classificationimage-classification+3

Parametric Contrastive Learning

2021-07-26 · ICCV 2021 10 · Jiequan Cui, Zhisheng Zhong, Shu Liu, Bei Yu 외

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 i…

Contrastive LearningImage ClassificationLong-tail Learning

Contrastive Conditional-Unconditional Alignment for Long-tailed Diffusion Model

2025-07-11 · Fang Chen, Alex Villa, Gongbo Liang, Fuxing Li 외 arxiv

Training data for class-conditional image synthesis often exhibit a long-tailed distribution with limited amount of images for tail classes. Such an imbalance causes mode collapse and reduces the diversity of synthesized…

Image Generation

Targeted Supervised Contrastive Learning for Long-Tailed Recognition

2021-11-27 · CVPR 2022 1 · Tianhong Li, Peng Cao, Yuan Yuan, Lijie Fan 외

Real-world data often exhibits long tail distributions with heavy class imbalance, where the majority classes can dominate the training process and alter the decision boundaries of the minority classes. Recently, researc…

Contrastive LearningLong-tail Learning

Rebalanced Siamese Contrastive Mining for Long-Tailed Recognition

2022-03-22 · Zhisheng Zhong, Jiequan Cui, Zeming Li, Eric Lo 외

Deep neural networks perform poorly on heavily class-imbalanced datasets. Given the promising performance of contrastive learning, we propose Rebalanced Siamese Contrastive Mining (ResCom) to tackle imbalanced recognitio…

Contrastive LearningLong-tail LearningRepresentation Learning