paper-with-me

Papers

Class-Imbalanced Semi-Supervised Learning

2020-02-17 · Minsung Hyun, Jisoo Jeong, Nojun Kwak

Semi-Supervised Learning (SSL) has achieved great success in overcoming the difficulties of labeling and making full use of unlabeled data. However, SSL has a limited assumption that the numbers of samples in different classes are balanced, and many SSL algorithms show lower performance for the datasets with the imbalanced class distribution. In this paper, we introduce a task of class-imbalanced semi-supervised learning (CISSL), which refers to semi-supervised learning with class-imbalanced data. In doing so, we consider class imbalance in both labeled and unlabeled sets. First, we analyze existing SSL methods in imbalanced environments and examine how the class imbalance affects SSL methods. Then we propose Suppressed Consistency Loss (SCL), a regularization method robust to class imbalance. Our method shows better performance than the conventional methods in the CISSL environment. In particular, the more severe the class imbalance and the smaller the size of the labeled data, the better our method performs.

📄 PDF Abstract BibTeX arXiv:2002.06815

Code (1)

MinsungHyun/Class-Imbalanced-Semi-Supervised-Learning 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Cluster-Guided Semi-Supervised Domain Adaptation for Imbalanced Medical Image Classification

2023-03-02 · Shota Harada, Ryoma Bise, Kengo Araki, Akihiko Yoshizawa 외

Semi-supervised domain adaptation is a technique to build a classifier for a target domain by modifying a classifier in another (source) domain using many unlabeled samples and a small number of labeled samples from the …

ClusteringDomain Adaptationimage-classificationImage Classification+3

Rethinking the Value of Labels for Improving Class-Imbalanced Learning

2020-06-13 · NeurIPS 2020 12 · Yuzhe Yang, Zhi Xu

Real-world data often exhibits long-tailed distributions with heavy class imbalance, posing great challenges for deep recognition models. We identify a persisting dilemma on the value of labels in the context of imbalanc…

Long-tail Learning

SeMi: When Imbalanced Semi-Supervised Learning Meets Mining Hard Examples

2025-01-10 · Yin Wang, Zixuan Wang, Hao Lu, Zhen Qin 외

Semi-Supervised Learning (SSL) can leverage abundant unlabeled data to boost model performance. However, the class-imbalanced data distribution in real-world scenarios poses great challenges to SSL, resulting in performa…

Network Embedding with Completely-imbalanced Labels

2020-07-07 · IEEE Transactions on Knowledge and Data Engineering 2020 2 · Zheng Wang, Xiaojun Ye, Chaokun Wang, Jian Cui 외

Network embedding, aiming to project a network into a low-dimensional space, is increasingly becoming a focus of network research. Semi-supervised network embedding takes advantage of labeled data, and has shown promisin…

Network Embedding

CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning

2021-02-18 · CVPR 2021 1 · Chen Wei, Kihyuk Sohn, Clayton Mellina, Alan Yuille 외

Semi-supervised learning on class-imbalanced data, although a realistic problem, has been under studied. While existing semi-supervised learning (SSL) methods are known to perform poorly on minority classes, we find that…