# IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilization

arXiv: https://arxiv.org/abs/2308.13168 · HTML: https://mlsanity.com/paper/2308.13168/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 47 references that are in the map.
- First posted on arXiv 25 Aug 2023.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [ReAct: Out-of-distribution Detection With Rectified Activations](https://mlsanity.com/paper/2111.12797/) (2021)
- [Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning](https://mlsanity.com/paper/1606.04586/) (2016)
- [ViM: Out-Of-Distribution with Virtual-logit Matching](https://mlsanity.com/paper/2203.10807/) (2022)
- [ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring](https://mlsanity.com/paper/1911.09785/) (2019)
- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [Learning with Pseudo-Ensembles](https://mlsanity.com/paper/1412.4864/) (2014)
- [FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning](https://mlsanity.com/paper/2205.07246/) (2022)
- [ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2106.05095/) (2021)
- [CoMatch: Semi-supervised Learning with Contrastive Graph Regularization](https://mlsanity.com/paper/2011.11183/) (2020)
- [SimMatch: Semi-supervised Learning with Similarity Matching](https://mlsanity.com/paper/2203.06915/) (2022)
- [USB: A Unified Semi-supervised Learning Benchmark for Classification](https://mlsanity.com/paper/2208.07204/) (2022)
- [OVANet: One-vs-All Network for Universal Domain Adaptation](https://mlsanity.com/paper/2104.03344/) (2021)
- [Multi-Task Curriculum Framework for Open-Set Semi-Supervised Learning](https://mlsanity.com/paper/2007.11330/) (2020)
- [OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers](https://mlsanity.com/paper/2105.14148/) (2021)
- [Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learning](https://mlsanity.com/paper/2108.05617/) (2021)

## Built on by (most cited first, 23 of 23)

- [UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2410.10777/) (2024)
- [Robust Semi-supervised Learning by Wisely Leveraging Open-set Data](https://mlsanity.com/paper/2405.06979/) (2024)
- [DebGCD: Debiased Learning with Distribution Guidance for Generalized Category Discovery](https://mlsanity.com/paper/2504.04804/) (2025)
- [Constructing and Exploring Intermediate Domains in Mixed Domain Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2404.08951/) (2024)
- [MOS: Modeling Object-Scene Associations in Generalized Category Discovery](https://mlsanity.com/paper/2503.12035/) (2025)
- [PG-LBO: Enhancing High-Dimensional Bayesian Optimization with Pseudo-Label and Gaussian Process Guidance](https://mlsanity.com/paper/2312.16983/) (2023)
- [CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image Collections](https://mlsanity.com/paper/2411.19346/) (2024)
- [Semi-Supervised Object Detection with Uncurated Unlabeled Data for Remote Sensing Images](https://mlsanity.com/paper/2310.05498/) (2023)
- [Data Can Speak for Itself: Quality-guided Utilization of Wireless Synthetic Data](https://mlsanity.com/paper/2506.23174/) (2025)
- [ProSub: Probabilistic Open-Set Semi-Supervised Learning with Subspace-Based Out-of-Distribution Detection](https://mlsanity.com/paper/2407.11735/) (2024)
- [SCOMatch: Alleviating Overtrusting in Open-set Semi-supervised Learning](https://mlsanity.com/paper/2409.17512/) (2024)
- [Re-Evaluating the Impact of Unseen-Class Unlabeled Data on Semi-Supervised Learning Model](https://mlsanity.com/paper/2503.00884/) (2025)
- [Unsupervised Learning for Class Distribution Mismatch](https://mlsanity.com/paper/2505.06948/) (2025)
- [Diversify and Conquer: Open-set Disagreement for Robust Semi-supervised Learning with Outliers](https://mlsanity.com/paper/2505.24443/) (2025)
- [Semi-Supervised Hierarchical Open-Set Classification](https://mlsanity.com/paper/2601.16541/) (2026)
- [Diverse Teacher-Students for Deep Safe Semi-Supervised Learning under Class Mismatch](https://mlsanity.com/paper/2405.16093/) (2024)
- [From Obstacles to Resources: Semi-supervised Learning Faces Synthetic Data Contamination](https://mlsanity.com/paper/2405.16930/) (2024)
- [Collaborative Feature-Logits Contrastive Learning for Open-Set Semi-Supervised Object Detection](https://mlsanity.com/paper/2411.13001/) (2024)
- [Let the Void Be Void: Robust Open-Set Semi-Supervised Learning via Selective Non-Alignment](https://mlsanity.com/paper/2504.12569/) (2025)
- [Open-Set Semi-Supervised Learning for Long-Tailed Medical Datasets](https://mlsanity.com/paper/2505.14846/) (2025)
- [CaliMatch: Adaptive Calibration for Improving Safe Semi-supervised Learning](https://mlsanity.com/paper/2508.00922/) (2025)
- [SafeECGMatch: Calibration-Aware Joint Frequency and Time Space Semi-Supervised Learning for Open-Set ECG Classification](https://mlsanity.com/paper/2606.08037/) (2026)
- [Geometric Gradient Rectification for Safe Open-Set Semi-Supervised Learning](https://mlsanity.com/paper/2606.26973/) (2026)

## Abstract (arXiv)

Semi-supervised learning (SSL) aims to leverage massive unlabeled data when labels are expensive to obtain. Unfortunately, in many real-world applications, the collected unlabeled data will inevitably contain unseen-class outliers not belonging to any of the labeled classes. To deal with the challenging open-set SSL task, the mainstream methods tend to first detect outliers and then filter them out. However, we observe a surprising fact that such approach could result in more severe performance degradation when labels are extremely scarce, as the unreliable outlier detector may wrongly exclude a considerable portion of valuable inliers. To tackle with this issue, we introduce a novel open-set SSL framework, IOMatch, which can jointly utilize inliers and outliers, even when it is difficult to distinguish exactly between them. Specifically, we propose to employ a multi-binary classifier in combination with the standard closed-set classifier for producing unified open-set classification targets, which regard all outliers as a single new class. By adopting these targets as open-set pseudo-labels, we optimize an open-set classifier with all unlabeled samples including both inliers and outliers. Extensive experiments have shown that IOMatch significantly outperforms the baseline methods across different benchmark datasets and different settings despite its remarkable simplicity. Our code and models are available at https://github.com/nukezil/IOMatch.