paper-with-me

Papers

Learning Label Refinement and Threshold Adjustment for Imbalanced Semi-Supervised Learning

2024-07-07 · Zeju Li, Ying-Qiu Zheng, Chen Chen, Saad Jbabdi

Semi-supervised learning (SSL) algorithms struggle to perform well when exposed to imbalanced training data. In this scenario, the generated pseudo-labels can exhibit a bias towards the majority class, and models that employ these pseudo-labels can further amplify this bias. Here we investigate pseudo-labeling strategies for imbalanced SSL including pseudo-label refinement and threshold adjustment, through the lens of statistical analysis. We find that existing SSL algorithms which generate pseudo-labels using heuristic strategies or uncalibrated model confidence are unreliable when imbalanced class distributions bias pseudo-labels. To address this, we introduce SEmi-supervised learning with pseudo-label optimization based on VALidation data (SEVAL) to enhance the quality of pseudo-labelling for imbalanced SSL. We propose to learn refinement and thresholding parameters from a partition of the training dataset in a class-balanced way. SEVAL adapts to specific tasks with improved pseudo-labels accuracy and ensures pseudo-labels correctness on a per-class basis. Our experiments show that SEVAL surpasses state-of-the-art SSL methods, delivering more accurate and effective pseudo-labels in various imbalanced SSL situations. SEVAL, with its simplicity and flexibility, can enhance various SSL techniques effectively. The code is publicly available (https://github.com/ZerojumpLine/SEVAL).

📄 PDF Abstract BibTeX arXiv:2407.05370

Code (1)

zerojumpline/seval 공식 구현 pytorch

Tasks

Pseudo Label

Similar Papers 제목 키워드 기반

Incorporating Improved Sinusoidal Threshold-based Semi-supervised Method and Diffusion Models for Osteoporosis Diagnosis

2024-03-11 · Wenchi Ke

Osteoporosis is a common skeletal disease that seriously affects patients' quality of life. Traditional osteoporosis diagnosis methods are expensive and complex. The semi-supervised model based on diffusion model and cla…

Pseudo Label

SemiGPC: Distribution-Aware Label Refinement for Imbalanced Semi-Supervised Learning Using Gaussian Processes

2023-11-03 · Abdelhak Lemkhenter, Manchen Wang, Luca Zancato, Gurumurthy Swaminathan 외

In this paper we introduce SemiGPC, a distribution-aware label refinement strategy based on Gaussian Processes where the predictions of the model are derived from the labels posterior distribution. Differently from other…

Gaussian Processes

Graph-Based Bidirectional Transformer Decision Threshold Adjustment Algorithm for Class-Imbalanced Molecular Data

2024-06-10 · Nicole Hayes, Ekaterina Merkurjev, Guo-Wei Wei

Data sets with imbalanced class sizes, where one class size is much smaller than that of others, occur exceedingly often in many applications, including those with biological foundations, such as disease diagnosis and dr…

Drug DiscoverySelf-Supervised Learning

FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning

2022-05-15 · Yidong Wang, Hao Chen, Qiang Heng, Wenxin Hou 외

Semi-supervised Learning (SSL) has witnessed great success owing to the impressive performances brought by various methods based on pseudo labeling and consistency regularization. However, we argue that existing methods …

FairnessSemi-Supervised Image Classification

BaCon: Boosting Imbalanced Semi-supervised Learning via Balanced Feature-Level Contrastive Learning

2024-03-04 · Qianhan Feng, Lujing Xie, Shijie Fang, Tong Lin

Semi-supervised Learning (SSL) reduces the need for extensive annotations in deep learning, but the more realistic challenge of imbalanced data distribution in SSL remains largely unexplored. In Class Imbalanced Semi-sup…

Contrastive Learning