rabbitboss/awesome-realistic-semi-supervised-learning

An awesome paper list of Semi-Supervised Learning under realistic settings.

Awesome-Realistic-Semi-Supervised-Learning

An awesome paper list of Semi-Supervised Learning (SSL) under realistic (Class-Imbalanced & Open-Set & Open-World) settings.

If you would like to add literature or have other requests, please contact [email protected]. We will update the list of papers regularly to keep it up to date. 😁

---

Open-Set SSL

• [ AAAI-2024 ] Unknown-Aware Graph Regularization for Robust Semi-supervised Learning from Uncurated Data [paper] [code]
• [ AAAI-2024 ] ANEDL: Adaptive Negative Evidential Deep Learning for Open-Set Semi-Supervised Learning [paper]
• [ ICCV-2023 ] Rethinking Safe Semi-supervised Learning: Transferring the Open-set Problem to A Close-set One [paper]
• [ ICCV-2023 ] SSB: Simple but Strong Baseline for Boosting Performance of Open-Set Semi-Supervised Learning [paper] [code]
• [ ICCV-2023 ] Semi-Supervised Learning via Weight-aware Distillation under Class Distribution Mismatch [paper] [code]
• [ ICCV-2023 ] IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilization [paper] [code]
• [ KDD-2023 ] Open-Set Semi-Supervised Text Classification with Latent Outlier Softening [paper] [code]
• [ ICML-2023 ] Bidirectional Adaptation for Robust Semi-Supervised Learning with Inconsistent Data Distributions [paper]
• [ CVPR-2023 ] Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learning [paper] [code]
• [ ICLR-2023 ] RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data [paper] [code]
• [ Arxiv-2023 ] Improving Open-Set Semi-Supervised Learning with Self-Supervision [paper]
• [ TMLR-2023 ] On Pseudo-Labeling for Class-Mismatch Semi-Supervised Learning [paper]
• [ NeurIPS-2022-Workshop ] Semi-supervised Learning from Uncurated Echocardiogram Images with Fix-A-Step [paper]
• [ AAAI-2022 ] Not All Parameters Should Be Treated Equally: Deep Safe Semi-Supervised Learning under Class Distribution Mismatch [paper] [code]
• [ CVPR-2022 ] Safe-Student for Safe Deep Semi-Supervised Learning with Unseen-Class Unlabeled Data [paper] [code]
• [ CVPR-2022 ] Class-Aware Contrastive Semi-Supervised Learning [paper] [code]
• [ TMM-2022 ] They are Not Completely Useless: Towards Recycling Transferable Unlabeled Data for Class-Mismatched Semi-Supervised Learning [paper] [code]
• [ ICDM-2022 ] How Out-of-Distribution Data Hurts Semi-Supervised Learning [paper]
• [ NeurIPS-2021 ] Universal Semi-Supervised Learning [paper] [code]
• [ NeurIPS-2021 ] OpenMatch: Open-Set Semi-supervised Learning with Open-set Consistency Regularization [paper] [code]
• [ ICCV-2021 ] Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learning [paper] [code]
• [ Arxiv-2021 ] An Empirical Study and Analysis on Open-Set Semi-Supervised Learning [paper]
• [ ECCV-2020 ] Multi-task curriculum framework for open-set semi-supervised learning [paper] [code]
• [ ICML-2020 ] Safe deep semi-supervised learning for unseen-class unlabeled data [paper] [code]
• [ AAAI-2020 ] Semi-Supervised Learning under Class Distribution Mismatch [paper]
• [ NeurIPS-2018 ] Realistic Evaluation of Deep Semi-Supervised Learning Algorithms [paper] [code]

---

Open-World SSL

• [ CVPR-2024 ] Targeted Representation Alignment for Open-World Semi-Supervised Learning

• [ AAAI-2024 ] Semi-supervised Open-World Object Detection [paper] [code]

• [ NeurIPS-2023 ] A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learning [paper] [code]

• [ NeurIPS-2023 ] Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning [paper] [code]

• [ CIKM-2023 ] WOT-Class: Weakly Supervised Open-world Text Classification [paper]

• [ ACL-ARR-2023 ] OW-Class: Open-world Semi-supervised Text Classification [paper]

• [ NeurIPS-2022 ] Robust Semi-Supervised Learning when Not All Classes have Labels [paper] [code]

• [ ICLR-2022 ] Open-World Semi-Supervised Learning [paper] [code]

• [ ECCV-2022 ] OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning [paper] [code]

• [ ECCV-2022 ] Towards Realistic Semi-Supervised Learning [paper] [code]

---

Class-Imbalanced SSL

• [ ARXIV-2024 ] SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learning [paper] [code]

• [ CVPR-2024 ] CDMAD: Class-Distribution-Mismatch-Aware Debiasing for Class-Imbalanced Semi-Supervised Learning [paper] [code]

• [ CVPR-2024 ] BEM: Balanced and Entropy-based Mix for Long-Tailed Semi-Supervised Learning [paper]

• [ AAAI-2024 ] Three Heads Are Better Than One: Complementary Experts for Long-Tailed Semi-supervised Learning [paper] [code]

• [ AAAI-2024 ] BaCon: Boosting Imbalanced Semi-Supervised Learning via Balanced Feature-Level Contrastive Learning [paper]

• [ AAAI-2024 ] Twice Class Bias Correction for Imbalanced Semi-Supervised Learning [paper] [code]

• [ ICCV-2023 ] Towards Semi-supervised Learning with Non-random Missing Labels [paper] [code]

• [ CVPR-2023 ] Towards Realistic Long-Tailed Semi-Supervised Learning: Consistency Is All You Need [paper] [code]

• [ ICLR-2023 ] InPL: Pseudo-labeling the Inliers First for Imbalanced Semi-supervised Learning [paper]

• [ ICLR-2023 ] Imbalanced Semi-supervised Learning with Bias Adaptive Classifier [paper] [code]

• [ ACL-2023 ] Prototype-Guided Pseudo Labeling for Semi-Supervised Text Classification [paper]

• [ WACV-2023 ] Unifying Distribution Alignment as a Loss for Imbalanced Semi-supervised Learning [paper]

• [ WACV-2023 ] Dynamic Re-weighting for Long-tailed Semi-supervised Learning [paper]

• [ 2023 ] Towards Semi-Supervised Learning with Non-Random Missing Labels [paper]

• [ ICLR-2022 ] On Non-Random Missing Labels in Semi-Supervised Learning [paper] [code]

• [ ICML-2022 ] Smoothed Adaptive Weighting for Imbalanced SSL: Improve Reliability Against Unknown Distribution Data [paper] [code]

• [ ICML-2022 ] Class-Imbalanced Semi-Supervised Learning with Adaptive Thresholding [paper] [code]

• [ ECCV-2022 ] RDA: Reciprocal Distribution Alignment for Robust Semi-supervised Learning [paper] [code]

• [ CVPR-2022-Workshop ] SaR: Self-adaptive Refinement on Pseudo Labels for Multiclass-Imbalanced Semi-supervised Learning [paper]

• [ CVPR-2022 ] DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced SSL [paper] [code]

• [ CVPR-2022 ] Debiased Learning from Naturally Imbalanced Pseudo-Labels [paper] [code]

• [ CVPR-2022 ] CoSSL: Co-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learning [paper] [code]

• [ CVPR-2022 ] DC-SSL: Addressing Mismatched Class Distribution in Semi-Supervised Learning [paper]

• [ Arxiv-2022 ] An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learning [paper]

• [ Arxiv-2022 ] Robust and Efficient Imbalanced Positive-Unlabeled Learning with Self-supervision [paper]

• [ NeurIPS-2021 ] ABC: Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learning [paper] [code]

• [ Arxiv-2021 ] Rethinking Re-Sampling in Imbalanced Semi-Supervised Learning [paper]

• [ CVPR-2021 ] CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning [paper] [code]

• [ IJCAI-2021 ] Positive-Unlabeled Learning from Imbalanced Data [paper]

• [ NeurIPS-2020 ] Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning [paper] [code]

• [ NeurIPS-2020 ] Rethinking the Value of Labels for Improving Class-Imbalanced Learning [paper]

  ---

  Novel Class Discovery

• [ ICCV-2023 ] Class-relation Knowledge Distillation for Novel Class Discovery [paper]

• [ ICCV-2023 ] Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discovery [paper] [code]

• [ CVPR-2023 ] PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery [paper] [code]

• [ CVPR-2023 ] Bootstrap Your Own Prior: Towards Distribution-Agnostic Novel Class Discovery [paper] [code]

• [ CVPR-2023 ] Modeling Inter-Class and Intra-Class Constraints in Novel Class Discovery [paper] [code]