paper-with-me

Papers

Semi-supervised Contrastive Outlier removal for Pseudo Expectation Maximization (SCOPE)

2022-06-28 · Sumeet Menon, David Chapman

Semi-supervised learning is the problem of training an accurate predictive model by combining a small labeled dataset with a presumably much larger unlabeled dataset. Many methods for semi-supervised deep learning have been developed, including pseudolabeling, consistency regularization, and contrastive learning techniques. Pseudolabeling methods however are highly susceptible to confounding, in which erroneous pseudolabels are assumed to be true labels in early iterations, thereby causing the model to reinforce its prior biases and thereby fail to generalize to strong predictive performance. We present a new approach to suppress confounding errors through a method we describe as Semi-supervised Contrastive Outlier removal for Pseudo Expectation Maximization (SCOPE). Like basic pseudolabeling, SCOPE is related to Expectation Maximization (EM), a latent variable framework which can be extended toward understanding cluster-assumption deep semi-supervised algorithms. However, unlike basic pseudolabeling which fails to adequately take into account the probability of the unlabeled samples given the model, SCOPE introduces an outlier suppression term designed to improve the behavior of EM iteration given a discrimination DNN backbone in the presence of outliers. Our results show that SCOPE greatly improves semi-supervised classification accuracy over a baseline, and furthermore when combined with consistency regularization achieves the highest reported accuracy for the semi-supervised CIFAR-10 classification task using 250 and 4000 labeled samples. Moreover, we show that SCOPE reduces the prevalence of confounding errors during pseudolabeling iterations by pruning erroneous high-confidence pseudolabeled samples that would otherwise contaminate the labeled set in subsequent retraining iterations.

📄 PDF Abstract BibTeX arXiv:2206.14261

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learning

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Semi-LAR: Semi-supervised Contrastive Learning with Linear Attention for Removal of Nighttime Flares

2026-05-18 · Xiyu Zhu, Wei Wang, Kui Jiang, Zhengguo Li arxiv

Lens flare removal is challenging due to the large spatial extent of flare artifacts and their entanglement with scene structures, while existing methods heavily rely on large-scale paired data. We propose a semi-supervi…

Contrastive LearningFlare Removal

SemiDDM-Weather: A Semi-supervised Learning Framework for All-in-one Adverse Weather Removal

2024-09-29 · Fang Long, Wenkang Su, Zixuan Li, Lei Cai 외

Adverse weather removal aims to restore clear vision under adverse weather conditions. Existing methods are mostly tailored for specific weather types and rely heavily on extensive labeled data. In dealing with these two…

AllDenoising

RCPS: Rectified Contrastive Pseudo Supervision for Semi-Supervised Medical Image Segmentation

2023-01-13 · Xiangyu Zhao, Zengxin Qi, Sheng Wang, Qian Wang 외

Medical image segmentation methods are generally designed as fully-supervised to guarantee model performance, which require a significant amount of expert annotated samples that are high-cost and laborious. Semi-supervis…

Contrastive LearningImage SegmentationMedical Image SegmentationSegmentation+2

CLAF: Contrastive Learning with Augmented Features for Imbalanced Semi-Supervised Learning

2023-12-15 · Bowen Tao, Lan Li, Xin-Chun Li, De-Chuan Zhan

Due to the advantages of leveraging unlabeled data and learning meaningful representations, semi-supervised learning and contrastive learning have been progressively combined to achieve better performances in popular app…

Contrastive Learningimage-classificationImage Classification

Integrating Distribution Matching into Semi-Supervised Contrastive Learning for Labeled and Unlabeled Data

2026-01-08 · Shogo Nakayama, Masahiro Okuda arxiv

The advancement of deep learning has greatly improved supervised image classification. However, labeling data is costly, prompting research into unsupervised learning methods such as contrastive learning. In real-world s…

Contrastive LearningImage Classification