paper-with-me

홈 › Papers

UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning

2022-03-28 · CVPR 2022 1 · Nazmul Karim, Mamshad Nayeem Rizve, Nazanin Rahnavard, Ajmal Mian, Mubarak Shah

Supervised deep learning methods require a large repository of annotated data; hence, label noise is inevitable. Training with such noisy data negatively impacts the generalization performance of deep neural networks. To combat label noise, recent state-of-the-art methods employ some sort of sample selection mechanism to select a possibly clean subset of data. Next, an off-the-shelf semi-supervised learning method is used for training where rejected samples are treated as unlabeled data. Our comprehensive analysis shows that current selection methods disproportionately select samples from easy (fast learnable) classes while rejecting those from relatively harder ones. This creates class imbalance in the selected clean set and in turn, deteriorates performance under high label noise. In this work, we propose UNICON, a simple yet effective sample selection method which is robust to high label noise. To address the disproportionate selection of easy and hard samples, we introduce a Jensen-Shannon divergence based uniform selection mechanism which does not require any probabilistic modeling and hyperparameter tuning. We complement our selection method with contrastive learning to further combat the memorization of noisy labels. Extensive experimentation on multiple benchmark datasets demonstrates the effectiveness of UNICON; we obtain an 11.4% improvement over the current state-of-the-art on CIFAR100 dataset with a 90% noise rate. Our code is publicly available

📄 PDF Abstract BibTeX arXiv:2203.14542

Code (1)

nazmul-karim170/unicon-noisy-label 공식 구현 pytorch

Tasks

Contrastive LearningLearning with noisy labelsMemorization

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

UniCon+: ICTCAS-UCAS Submission to the AVA-ActiveSpeaker Task at ActivityNet Challenge 2022

2022-06-22 · Yuanhang Zhang, Susan Liang, Shuang Yang, Shiguang Shan

This report presents a brief description of our winning solution to the AVA Active Speaker Detection (ASD) task at ActivityNet Challenge 2022. Our underlying model UniCon+ continues to build on our previous work, the Uni…

Active Speaker DetectionAudio-Visual Active Speaker Detection

UniCon: Unified Framework for Efficient Contrastive Alignment via Kernels

2026-04-17 · Hangke Sui, Yuqing Wang, Minh N Do arxiv

Contrastive objectives power state-of-the-art multimodal models, but their training remains slow, relying on long stochastic optimization. We propose a Unified Framework for Efficient Contrastive Alignment via Kernels (U…

Stochastic Optimization

Universum-inspired Supervised Contrastive Learning

2022-04-22 · Aiyang Han, Chuanxing Geng, Songcan Chen

As an effective data augmentation method, Mixup synthesizes an extra amount of samples through linear interpolations. Despite its theoretical dependency on data properties, Mixup reportedly performs well as a regularizer…

Contrastive LearningData Augmentation

UniConvNet: Expanding Effective Receptive Field while Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale

2025-08-12 · Yuhao Wang, Wei Xi arxiv

Convolutional neural networks (ConvNets) with large effective receptive field (ERF), still in their early stages, have demonstrated promising effectiveness while constrained by high parameters and FLOPs costs and disrupt…

Open-Linguistic Concept Unified Learning for Cross-Site Interpretable Dermatology Image Diagnosis

2026-08-04 · Chengyu Wu, Junpeng Tan, Wanxiang Luo, Yaqi Wang 외 arxiv

Human-interpretable computer-aided diagnosis is crucial for clinical decision making. Concept-based models excel by providing transparent reasoning and enabling post-hoc, clinician-in-the-loop interventions. However, the…

Decision Making