paper-with-me

홈 › Papers

Learning with Noisy labels via Self-supervised Adversarial Noisy Masking

2023-02-14 · CVPR 2023 1 · Yuanpeng Tu, Boshen Zhang, Yuxi Li, Liang Liu, Jian Li, Jiangning Zhang, Yabiao Wang, Chengjie Wang, Cai Rong Zhao

Collecting large-scale datasets is crucial for training deep models, annotating the data, however, inevitably yields noisy labels, which poses challenges to deep learning algorithms. Previous efforts tend to mitigate this problem via identifying and removing noisy samples or correcting their labels according to the statistical properties (e.g., loss values) among training samples. In this paper, we aim to tackle this problem from a new perspective, delving into the deep feature maps, we empirically find that models trained with clean and mislabeled samples manifest distinguishable activation feature distributions. From this observation, a novel robust training approach termed adversarial noisy masking is proposed. The idea is to regularize deep features with a label quality guided masking scheme, which adaptively modulates the input data and label simultaneously, preventing the model to overfit noisy samples. Further, an auxiliary task is designed to reconstruct input data, it naturally provides noise-free self-supervised signals to reinforce the generalization ability of deep models. The proposed method is simple and flexible, it is tested on both synthetic and real-world noisy datasets, where significant improvements are achieved over previous state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:2302.06805

Code (1)

yuanpengtu/SANM 공식 구현 pytorch

Tasks

Image ClassificationLearning with noisy labels

Similar Papers 제목 키워드 기반

Improving Medical Image Classification in Noisy Labels Using Only Self-supervised Pretraining

2023-08-08 · Bidur Khanal, Binod Bhattarai, Bishesh Khanal, Cristian A. Linte

Noisy labels hurt deep learning-based supervised image classification performance as the models may overfit the noise and learn corrupted feature extractors. For natural image classification training with noisy labeled d…

Classificationimage-classificationImage ClassificationLearning with noisy labels+2

Self-semi-supervised Learning to Learn from NoisyLabeled Data

2020-11-03 · Jiacheng Wang, Yue Ma, Shuang Gao

The remarkable success of today's deep neural networks highly depends on a massive number of correctly labeled data. However, it is rather costly to obtain high-quality human-labeled data, leading to the active research …

Co-learning: Learning from Noisy Labels with Self-supervision

2021-08-05 · Cheng Tan, Jun Xia, Lirong Wu, Stan Z. Li

Noisy labels, resulting from mistakes in manual labeling or webly data collecting for supervised learning, can cause neural networks to overfit the misleading information and degrade the generalization performance. Self-…

Learning with noisy labelsSelf-Supervised Learning

How does self-supervised pretraining improve robustness against noisy labels across various medical image classification datasets?

2024-01-15 · Bidur Khanal, Binod Bhattarai, Bishesh Khanal, Cristian Linte

Noisy labels can significantly impact medical image classification, particularly in deep learning, by corrupting learned features. Self-supervised pretraining, which doesn't rely on labeled data, can enhance robustness a…

Contrastive Learningimage-classificationImage ClassificationMedical Image Classification+1

Combining Self-Supervised and Supervised Learning with Noisy Labels

2020-11-16 · Yongqi Zhang, HUI ZHANG, Quanming Yao, Jun Wan

Since convolutional neural networks (CNNs) can easily overfit noisy labels, which are ubiquitous in visual classification tasks, it has been a great challenge to train CNNs against them robustly. Various methods have bee…

Learning with noisy labelsRepresentation LearningSelf-Supervised Learning