# Class-Distribution-Aware Pseudo Labeling for Semi-Supervised Multi-Label Learning

arXiv: https://arxiv.org/abs/2305.02795 · HTML: https://mlsanity.com/paper/2305.02795/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 61 references that are in the map.
- First posted on arXiv 4 May 2023.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (2018)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [Asymmetric Loss For Multi-Label Classification](https://mlsanity.com/paper/2009.14119/) (2020)
- [ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring](https://mlsanity.com/paper/1911.09785/) (2019)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning](https://mlsanity.com/paper/2101.06329/) (2021)
- [FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning](https://mlsanity.com/paper/2205.07246/) (2022)
- [CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2102.09559/) (2021)
- [CoMatch: Semi-supervised Learning with Contrastive Graph Regularization](https://mlsanity.com/paper/2011.11183/) (2020)
- [Dash: Semi-Supervised Learning with Dynamic Thresholding](https://mlsanity.com/paper/2109.00650/) (2021)
- [Query2Label: A Simple Transformer Way to Multi-Label Classification](https://mlsanity.com/paper/2107.10834/) (2021)
- [General Multi-label Image Classification with Transformers](https://mlsanity.com/paper/2011.14027/) (2020)
- [Learning a Deep ConvNet for Multi-label Classification with Partial Labels](https://mlsanity.com/paper/1902.09720/) (2019)
- [Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning](https://mlsanity.com/paper/2007.08844/) (2020)
- [The Emerging Trends of Multi-Label Learning](https://mlsanity.com/paper/2011.11197/) (2020)
- [Learning to Predict Visual Attributes in the Wild](https://mlsanity.com/paper/2106.09707/) (2021)
- [Multi-Label Learning from Single Positive Labels](https://mlsanity.com/paper/2106.09708/) (2021)
- [ML-Decoder: Scalable and Versatile Classification Head](https://mlsanity.com/paper/2111.12933/) (2021)
- [Improving Pairwise Ranking for Multi-label Image Classification](https://mlsanity.com/paper/1704.03135/) (2017)
- [Large Loss Matters in Weakly Supervised Multi-Label Classification](https://mlsanity.com/paper/2206.03740/) (2022)
- [Semi-Supervised Multi-Modal Multi-Instance Multi-Label Deep Network with Optimal Transport](https://mlsanity.com/paper/2104.08489/) (2021)
- [Multi-label Classification with Partial Annotations using Class-aware Selective Loss](https://mlsanity.com/paper/2110.10955/) (2021)

## Built on by (most cited first, 16 of 16)

- [ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery](https://mlsanity.com/paper/2504.03755/) (2025)
- [Text-Region Matching for Multi-Label Image Recognition with Missing Labels](https://mlsanity.com/paper/2407.18520/) (2024)
- [Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training](https://mlsanity.com/paper/2404.06287/) (2024)
- [Correlative and Discriminative Label Grouping for Multi-Label Visual Prompt Tuning](https://mlsanity.com/paper/2504.09990/) (2025)
- [Rethinking Consistent Multi-Label Classification Under Inexact Supervision](https://mlsanity.com/paper/2510.04091/) (2025)
- [Are Multimodal Large Language Models Good Annotators for Image Tagging?](https://mlsanity.com/paper/2602.20972/) (2026)
- [Dual-Decoupling Learning and Metric-Adaptive Thresholding for Semi-Supervised Multi-Label Learning](https://mlsanity.com/paper/2407.18624/) (2024)
- [Semantic-guided Representation Learning for Multi-Label Recognition](https://mlsanity.com/paper/2504.03801/) (2025)
- [Representation-Level Counterfactual Calibration for Debiased Zero-Shot Recognition](https://mlsanity.com/paper/2510.26466/) (2025)
- [AROMMA: Unifying Olfactory Embeddings for Single Molecules and Mixtures](https://mlsanity.com/paper/2601.19561/) (2026)
- [FedHarmony: Harmonizing Heterogeneous Label Correlations in Federated Multi-Label Learning](https://mlsanity.com/paper/2604.28024/) (2026)
- [PLOOD: Partial Label Learning with Out-of-distribution Objects](https://mlsanity.com/paper/2403.06681/) (2024)
- [LEASE: Offline Preference-based Reinforcement Learning with High Sample Efficiency](https://mlsanity.com/paper/2412.21001/) (2024)
- [Semi-Supervised Learning with Balanced Deep Representation Distributions](https://mlsanity.com/paper/2603.21056/) (2026)
- [Bridging the Gap between Labeled and Unlabeled Data via Unified Flow with Feature Memory Bank](https://mlsanity.com/paper/2608.16681/) (2026)
- [Unlabeled Echoes: Pseudo-Labels and Genus-Aware Smoothing for Bat Call Recognition](https://mlsanity.com/paper/2609.11986/) (2026)

## Abstract (arXiv)

Pseudo-labeling has emerged as a popular and effective approach for utilizing unlabeled data. However, in the context of semi-supervised multi-label learning (SSMLL), conventional pseudo-labeling methods encounter difficulties when dealing with instances associated with multiple labels and an unknown label count. These limitations often result in the introduction of false positive labels or the neglect of true positive ones. To overcome these challenges, this paper proposes a novel solution called Class-Aware Pseudo-Labeling (CAP) that performs pseudo-labeling in a class-aware manner. The proposed approach introduces a regularized learning framework incorporating class-aware thresholds, which effectively control the assignment of positive and negative pseudo-labels for each class. Notably, even with a small proportion of labeled examples, our observations demonstrate that the estimated class distribution serves as a reliable approximation. Motivated by this finding, we develop a class-distribution-aware thresholding strategy to ensure the alignment of pseudo-label distribution with the true distribution. The correctness of the estimated class distribution is theoretically verified, and a generalization error bound is provided for our proposed method. Extensive experiments on multiple benchmark datasets confirm the efficacy of CAP in addressing the challenges of SSMLL problems.