• Home
  • Search
  • Out-of-Distribution Detection for Open-Set Semi-Supervised Medical Image Classification
  • Cite Icon2
  • https://doi.org/10.1145/3731715.3733412Copy DOI Icon

Out-of-Distribution Detection for Open-Set Semi-Supervised Medical Image Classification

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Semi-supervised learning (SSL) has been prevailed in medical image analysis field because it leverage unlabeled data for training powerful models without incurring extra high annotation cost. However, the existing SSL models face the challenge of performance degradation in open-set scenario where both in-distribution (ID) and out-of-distribution (OOD) samples are mixed in unlabeled data. The existing two-phases methods treat OOD detection and semi-supervised classification as two independent tasks which fail to reveal their mutual reinforcement ability. In this research, we introduce a joint optimization framework designed to enhance both the semi-supervised classification task and the OOD detection task through an iterative process. Specifically, our approach employs a unified model to assess the likelihood of images being OOD sample, subsequently filtering these instances from the pool of unlabeled data. The model parameters update and the OOD detection are optimized alternately. Additionally, to avoid the model overconfidence, we introduce logit normalization (Logit-Norm) loss to provide more reliable predictions. To validate the effectiveness of our method, we use the ISIC2018 dataset as the ID dataset and mix OOD samples from other medical image datasets to train classification model. Experimental results demonstrate that our method successfully mitigates the influence of OOD data on semi-supervised medical image classification performance while also improving OOD detection performance. The proposed framework successfully addresses the challenges posed by OOD samples in semi-supervised learning, offering a promising solution for medical image classification tasks that involve OOD data.

Similar Papers
  • PDF
  • Research Article
  • Citations3

Small Sample Time Series Classification Based on Data Augmentation and Semi-supervised Learning

  • Jun 26, 2024
  • Information Technology and Control
  • Jing-Jing Liu +4
  • Research Article
  • Citations18

SPLAL: Similarity-based pseudo-labeling with alignment loss for semi-supervised medical image classification

  • Nov 08, 2023
  • Biomedical Signal Processing and Control
  • Md Junaid Mahmood +4
  • Conference Article
  • Citations5

A Generative Bayesian Graph Attention Network for Semi-Supervised Classification on Scarce Data

  • Jul 18, 2021
  • Zhongtian Sun +4
  • Research Article
  • Citations22

Handling Imbalanced Data: Uncertainty-Guided Virtual Adversarial Training With Batch Nuclear-Norm Optimization for Semi-Supervised Medical Image Classification.

  • Jul 01, 2022
  • IEEE Journal of Biomedical and Health Informatics
  • Peng Liu +1
  • Research Article
  • Citations107

Deep virtual adversarial self-training with consistency regularization for semi-supervised medical image classification.

  • Feb 22, 2021
  • Medical Image Analysis
  • Xi Wang +5
  • Research Article
  • Citations17

Time-frequency based multi-task learning for semi-supervised time series classification

  • Nov 17, 2022
  • Information Sciences
  • Chixuan Wei +4
  • Research Article
  • Citations11

FaxMatch: Multi-Curriculum Pseudo-Labeling for semi-supervised medical image classification.

  • Feb 21, 2023
  • Medical Physics
  • Zhen Peng +6
  • Research Article
  • Citations16

Semi-supervised medical image classification via distance correlation minimization and graph attention regularization

  • Feb 21, 2024
  • Medical image analysis
  • Abel Díaz Berenguer +5
  • Research Article
  • Citations6

Enhanced Semi-Supervised Medical Image Classification Based on Dynamic Sample Reweighting and Pseudo-Label Guided Contrastive Learning (DSRPGC)

  • Nov 15, 2024
  • Mathematics
  • Kun Liu +2
  • Research Article

An open-set semi-supervised multi-task learning framework for context classification in biomedical texts.

  • Sep 01, 2025
  • Journal of biomedical informatics
  • Difei Tang +4
  • PDF
  • Research Article
  • Citations6

Leveraging Graph Convolutional Networks for Semi-supervised Learning in Multi-view Non-graph Data

  • Mar 01, 2025
  • Cognitive Computation
  • F Dornaika +2
  • Research Article
  • Citations1

Pseudo Labeling Collaborative Embedding Representation: A Multi-Channel GCNs Framework for Semi-Supervised Node Classification

  • Jan 01, 2024
  • IEEE Access
  • Mengnan Pang +3
  • Research Article

Semi-supervised Medical Image Classification Made Easier with Causality-Driven Learning.

  • May 22, 2026
  • IEEE journal of biomedical and health informatics
  • Chuankai Xu +3
  • Book Chapter
  • Citations10

Semi-supervised Medical Image Classification with Temporal Knowledge-Aware Regularization

  • Jan 01, 2022
  • Qiushi Yang +4
  • Book Chapter
  • Citations41

Semi-supervised Medical Image Classification with Global Latent Mixing

  • Jan 01, 2020
  • Prashnna Kumar Gyawali +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.