A curated list of most recent papers & codes in Learning with Partial/Complementary Labels
To be continued...
- Benchmarks & Leaderboard
- Papers & Code in 2023
- Papers & Code in 2022
- Papers & Code in 2021
- Papers & Code in 2020
- Papers & Code in 2019
- Papers & Code in 2018
- Papers & Code in 2017
Real-World partial-label benchmarks:
Notice: The following partial label learning data sets were collected and pre-processed by Prof. Min-Ling Zhang, with courtesy and proprietary to the authors of referred literatures on them. The pre-processed data sets can be used at your own risk and for academic purpose only. More information can be found in here.
| Dataset | Website | Paper |
|---|---|---|
| FG-NET data | [Download link] | [Paper] |
| Lost data | [Download link] | [Paper] |
| MSRCv2 data | [Download link] | [Paper] |
| BirdSong data | [Download link] | [Paper] |
| Soccer Player data | [Download link] | [Paper] |
| Yahoo! News | [Download link] | [Paper] |
| Mirflicker data | [Download link] | [Paper] |
Leaderboard, To be continued...
- Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical
- Does Label Smoothing Help Deep Partial Label Learning?
- [SEU PALM Lab] Learning with Partial-Label and Unlabeled Data: A Uniform Treatment for Supervision Redundancy and Insufficiency
- Partial Multi-View Multi-Label Classification via Semantic Invariance Learning and Prototype Modeling
- A General Framework for Learning from Weak Supervision
- Candidate Label Set Pruning: A Data-centric Perspective for Deep Partial-label Learning
- CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning.
[TKDE] [SEU PALM Lab] Dimensionality Reduction for Partial Label Learning: A Unified and Adaptive Approach
[MLJ] A Deep Model for Partial Multi-Label Image Classification with Curriculum Based Disambiguation
- Partial Label Supervision for Agnostic Generative Noisy Label Learning
- Understanding Self-Distillation and Partial Label Learning in Multi-Class Classification with Label Noise
- Uncertainty-Aware Partial-Label Learning
- Pseudo-labelling meets Label Smoothing for Noisy Partial Label Learning
- Appeal: Allow Mislabeled Samples the Chance to be Rectified in Partial Label Learning
- Enhancing Label Sharing Efficiency in Complementary-Label Learning with Label Augmentation
- Deep Learning with Partially Labeled Data for Radio Map Reconstruction.
- Towards Unbiased Exploration in Partial Label Learning
- Imprecise label learning: A unified framework for learning with various imprecise label configurations.
- Robust Representation Learning for Unreliable Partial Label Learning
- Pseudo Labels Regularization for Imbalanced Partial-Label Learning.
- Star Temporal Classification: Sequence Classification with Partially Labeled Data.
- Learning Reliable Representations for Incomplete Multi-View Partial Multi-Label Classification.
- A Confidence-based Partial Label Learning Model for Crowd-Annotated Named Entity Recognition
- Deep Duplex Learning for Weak Supervision.
- Learning from Stochastic Labels.
- Towards Mitigating the Problem of Insufficient and Ambiguous Supervision in Online Crowdsourcing Annotation.
- Active Learning with Partial Labels.
- Partial Label Learning for Emotion Recognition from EEG
- Solving Partial Label Learning Problem with Multi-Agent Reinforcement Learning.
- Adversary-aware partial label learning with label distillation.
- ARNet: Automatic Refinement Network for Noisy Partial Label Learning.
- Meta Objective Guided Disambiguation for Partial Label Learning.
- [SEU PALM Lab] Disentangled partial label learning.
- [SEU PALM Lab] Long-tailed partial label learning by head classifier and tail classifier cooperation.
- [SEU PALM Lab] Distilling reliable knowledge for instance-dependent partial label learning.
- Partial Label Learning with a Partner.
- Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning.
- Candidate Label Set Pruning: A Data-centric Perspective for Deep Partial-label Learning.
- [MLJ] Exploiting Counter-Examples for Active Learning with Partial-labels.
- [Neural Networks] Boosting Semi-Supervised Learning with Contrastive Complementary Labeling.
- [Pattern Recognition] Self-distillation and self-supervision for partial label learning.
- [SEU PALM Lab] Disambiguated Attention Embedding for Multi-Instance Partial-Label Learning.
- ALIM: Adjusting Label Importance Mechanism for Noisy Partial Label Learning.
- [SEU PALM Lab] Partial multi-label learning with probabilistic graphical disambiguation.
- [SEU PALM Lab] Learning From Biased Soft Labels.
- [SEU PALM Lab] Partial Label Learning with Dissimilarity Propagation guided Candidate Label Shrinkage.
- Candidate-aware Selective Disambiguation Based On Normalized Entropy for Instance-dependent Partial-label Learning.
- Learning in Imperfect Environment: Multi-Label Classification with Long-Tailed Distribution and Partial Labels.
- [SEU PALM Lab] Towards Effective Visual Representations for Partial-Label Learning.
- Rethinking the Learning Paradigm for Dynamic Facial Expression Recognition.
- [SEU PALM Lab] Complementary Classifier Induced Partial Label Learning.
- Partial-label Learning with Mixed Closed-set and Open-set Out-of-candidate Examples.
- [SEU PALM Lab] Unbiased risk estimator to multi-labeled complementary label learning.
- [SEU PALM Lab] Unreliable Partial Label Learning with Recursive Separation.
- Deep Partial Multi-Label Learning with Graph Disambiguation.
- [SEU PALM Lab] Progressive Purification for Instance-Dependent Partial Label Learning.
- [SEU PALM Lab] FREDIS: A Fusion Framework of Refinement and Disambiguation for Unreliable Partial Label Learning.
- Consistent Complementary-Label Learning via Order-Preserving Losses.
- Conformal Prediction with Partially Labeled Data.
- [SEU PALM Lab] Can Label-Specific Feature Help Partial-Label Learning?
- [SEU PALM Lab] Partial-Label Regression.
- Learning with Partial Labels from Semi-supervised Perspective.
- Long-Tailed Partial Label Learning via Dynamic Rebalancing.
- Partial Label Unsupervised Domain Adaptation with Class-Prototype Alignment.
- Mutual Partial Label Learning with Competitive Label Noise.
- [SEU PALM Lab] Decompositional Generation Process for Instance-Dependent Partial Label Learning.
- Reduction from Complementary-Label Learning to Probability Estimates.
- [TPAMI] A Unifying Probabilistic Framework for Partially Labeled Data Learning.
- [TPAMI] [SEU PALM Lab] On the Robustness of Average Losses for Partial-Label Learning.
- [TPAMI] CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning.
- [TPAMI] PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning.
- [TPAMI] [SEU PALM Lab] Towards enabling binary decomposition for partial multi-label learning.
- [TPAMI] [SEU PALM Lab] Variational label enhancement.
- [Pattern Recognition] GraphDPI: Partial label disambiguation by graph representation learning via mutual information maximization.
- [Neural Networks] Partial label learning: Taxonomy, analysis and outlook.
- [Neural Networks] Class-Imbalanced Complementary-Label Learning via Weighted Loss.
- [Science China Information Sciences] [SEU PALM Lab] Multi-Instance Partial-Label Learning: Towards Exploiting Dual Inexact Supervision.
- [TNNLS] Deep Double Incomplete Multi-View Multi-Label Learning With Incomplete Labels and Missing Views.
- SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning.
- Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks.
- [SEU PALM Lab] Submodular feature selection for partial label learning. [Paper] [Code]
- [SEU PALM Lab] Partial label learning with discriminative augmentation.
- Partial-Label Learning with Semantic Label Representations.
- [SEU PALM Lab] Revisiting consistency regularization for deep partial label learning. [Paper] [Code]
- Partial Label Learning via Label Influence Function.
- Multi-label classification with partial annotations using class-aware selective loss
- [SEU PALM Lab] Ambiguity-Induced Contrastive Learning for Instance-Dependent Partial Label Learning.
- Boosting Multi-Label Image Classification with Complementary Parallel Self-Distillation. [Paper]
- Exploring Binary Classification Hidden within Partial Label Learning.
- Deep Graph Matching for Partial Label Learning.
- Webly-Supervised Fine-Grained Recognition with Partial Label Learning.
- Structured Semantic Transfer for Multi-Label Recognition with Partial Labels
- Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels
- PiCO: Contrastive Label Disambiguation for Partial-Label Learning. [Paper][Code]
- Exploiting Class Activation Value for Partial-Label Learning. [Paper][Code]
- [TPAMI] [SEU PALM Lab] Adaptive graph guided disambiguation for partial label learning. [Paper][Supplement][Code]
- [TPAMI] Deep Partial Multi-View Learning.
- [TKDD] [SEU PALM Lab] Disambiguation enabled linear discriminant analysis for partial label dimensionality reduction. [Paper][Code]
- [TNNLS] Biased Complementary-Label Learning Without True Labels.
- [Pattern Recognition] Multi-Complementary and Unlabeled Learning for Arbitrary Losses and Models.
- [Machine Learning] [SEU PALM Lab]Partial label learning with emerging new labels.
- [AI] Distributed Semi-supervised Partial Label Learning Over Networks.
- [Neurocomputing] Learning with Proper Partial Labels.
- [Information Sciences] Dlsa: Semi-supervised partial label learning via dependence-maximized label set assignment.
- [SEU PALM Lab] Instance-Dependent Partial Label Learning. (oral) [Paper][Appendix][Code]
- Understanding Partial Multi-label Learning via Mutual Information. [Paper]
- [SEU PALM Lab] Partial label dimensionality reduction via confidence-based dependence maximization. [Paper][Code]
- Partial Multi-Label Learning with Meta Disambiguation. [Paper]
- [SEU PALM Lab] Discriminative complementary-label learning with weighted loss. [Paper][Code]
- Leveraged Weighted Loss for Partial Label Learning. [Paper][Supplement]
- Detecting the Fake Candidate Instances: Ambiguous Label Learning with Generative Adversarial Networks
- A Partial Label Metric Learning Algorithm for Class Imbalanced Data.
- [SEU PALM Lab] Learning from complementary labels via partial-output consistency regularization. [Paper][Code]
- Few-Shot Partial-Label Learning. [Paper]
- Joint Negative and Positive Learning for Noisy Labels. [Paper]
- [SEU PALM Lab] Exploiting unlabeled data via partial label assignment for multi-class semi-supervised learning. [Paper][Code]
- Adversarial Partial Multi-Label Learning with Label Disambiguation. [Paper]
- [SEU PALM Lab] Learning from Noisy Labels with Complementary Loss Functions. [Paper]
-
[TPAMI] [SEU PALM Lab] Partial multi-label learning via credible label elicitation. [Paper][Code]
-
[TPAMI] Partial Multi-Label Learning with Noisy Label Identification. [Paper]
-
[TNNLS] Top-k Partial Label Machine. [Paper]
-
[TNNLS] Learning From a Complementary-Label Source Domain: Theory and Algorithms. [Paper]
-
[TNNLS] Discriminative Metric Learning for Partial Label Learning.
-
[TNNLS] [SEU PALM Lab] Progressive enhancement of label distributions for partial multilabel learning.
-
[TMM] Generalized Large Margin kNN for Partial Label Learning. [Paper]
-
[TMM] Global-Local Label Correlation for Partial Multi-Label Learning. [Paper]
-
[Cybernetics] Prior Knowledge Regularized Self-Representation Model for Partial Multilabel Learning.
-
[ICASSP] On the power of deep but naive partial label learning.
- [SEU PALM Lab] Semi-supervised partial label learning via confidence-rated margin maximization. [Paper][Code]
- [SEU PALM Lab] Provably Consistent Partial-Label Learning. [Paper][Code]
- [SEU PALM Lab] Feature-induced manifold disambiguation for multi-view partial multi-label learning. [Paper][Code]
- [SEU PALM Lab] Progressive Identification of True Labels for Partial-Label Learning. [Paper][Code]
- Bridging Ordinary-Label Learning and Complementary-Label Learning. [Paper]
- Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels. [Paper]
- Learning with Multiple Complementary Labels. [Paper]
- Partial Multi-Label Learning via Multi-Subspace Representation. [Paper]
- Learning From Multi-Dimensional Partial Labels.
- [SEU PALM Lab] Multi-view partial multi-label learning with graph-based disambiguation. [Paper][Code]
- Partial Label Learning with Batch Label Correction. [Paper]
- Generative-Discriminative Complementary Learning. [Paper]
- Complementary Auxiliary Classifiers for Label-Conditional Text Generation. [Paper]
- Deep Discriminative CNN with Temporal Ensembling for Ambiguously-Labeled Image Classification.
- Network Cooperation with Progressive Disambiguation for Partial Label Learning. [Paper]
- Online Partial Label Learning.
- Learning with Noisy Partial Labels by Simultaneously Leveraging Global and Local Consistencies.
- [TNNLS] Large Margin Partial Label Machine.
- [Cybernetics] A Self-Paced Regularization Framework for Partial-Label Learning.
- [SEU PALM Lab] Adaptive Graph Guided Disambiguation for Partial Label Learning.
- Complementary-Label Learning for Arbitrary Losses and Models. [Paper]
- NLNL: Negative Learning for Noisy Labels. [Paper]
- Partial Label Learning with Unlabeled Data.
- Partial Label Learning by Semantic Difference Maximization.
- Learning a Deep ConvNet for Multi-Label Classification With Partial Labels
- Partial Label Learning with Self-Guided Retraining.
- [SEU PALM Lab] Partial Label Learning via Label Enhancement.
- [TKDE] GM-PLL: Graph Matching based Partial Label Learning.
[SEU PALM Lab]Towards Mitigating the Class-Imbalance Problem for Partial Label Learning
- Learning with Biased Complementary Labels. [Paper]
- Adversarial Complementary Learning for Weakly Supervised Object Localization. [Paper]
- Learning from Complementary Labels. [Paper]