- Hyperspectral-Image-Denoising-Benchmark
- Hyperspectral Denoising algorithm toolbox in Python
- 高光谱图像重构常用评价指标及其Python实现
- 遥感学报公众号 高光谱遥感数据集
- Hyperspectral Remote Sensing Scenes
Learning-with-Noisy-Labels
Benchmarks & Leaderboard
Real-world noisy-label bechmarks:
Dataset | Leaderboard Link | Website | Paper |
---|---|---|---|
CIFAR-10N | [Leaderboard] | [Website] | [Paper] |
CIFAR-100N | [Leaderboard] | [Website] | [Paper] |
Red Stanford Cars | N/A | [Website] | [Paper] |
Red Mini-ImageNet | N/A | [Website] | [Paper] |
Animal-10N | [Leaderboard] | [Website] | [Paper] |
Food-101N | N/A | [Website] | [Paper] |
Clothing1M | [Leaderboard] | [Website] | [Paper] |
Simulation of label noise: An Instance-Dependent Simulation Framework for Learning with Label Noise. [Paper]
This repo focus on papers after 2019, for previous works, please refer to (GitHub - subeeshvasu/Awesome-Learning-with-Label-Noise: A curated list of resources for Learning with Noisy Labels).
Papers & Code in 2023
ICLR 2023
- [UCSC REAL Lab] Distributionally Robust Post-hoc Classifiers under Prior Shifts. [Paper][Code]
- [UCSC REAL Lab] Mitigating Memorization of Noisy Labels via Regularization between Representations. [Paper & Code]
- On the Edge of Benign Overfitting: Label Noise and Overparameterization Level. [Paper & Code]
- Deep Learning From Crowdsourced Labels: Coupled Cross-Entropy Minimization, Identifiability, and Regularization. [Paper & Code]
- CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos. [Paper & Code]
- Learning to Segment from Noisy Annotations: A Spatial Correction Approach. [Paper & Code]
- Mutual Partial Label Learning with Competitive Label Noise. [Paper & Code]
- Memorization-Dilation: Modeling Neural Collapse Under Noise. [Paper & Code]
- Leveraging Unlabeled Data to Track Memorization . [Paper & Code]
- Quantifying and Mitigating the Impact of Label Errors on Model Disparity Metrics. [Paper & Code]
- When Source-Free Domain Adaptation Meets Learning with Noisy Labels. [Paper & Code]
- A law of adversarial risk, interpolation, and label noise. [Paper & Code]
- SoftMatch: Addressing the Quantity-Quality Tradeoff in Semi-supervised Learning. [Paper & Code]
- CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos. [Paper & Code]
- Does Decentralized Learning with Non-IID Unlabeled Data Benefit from Self Supervision?. [Paper & Code]
- Label Propagation with Weak Supervision . [Paper & Code]
- Mitigating Dataset Bias by Using Per-Sample Gradient. [Paper & Code]
- MCAL: Minimum Cost Human-Machine Active Labeling. [Paper & Code]
- Avoiding spurious correlations via logit correction. [Paper & Code]
- Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts . [Paper & Code]
- Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play. [Paper & Code]
- Towards Lightweight, Model-Agnostic and Diversity-Aware Active Anomaly Detection. [Paper & Code]
- Weakly Supervised Explainable Phrasal Reasoning with Neural Fuzzy Logic. [Paper & Code]
- Towards Addressing Label Skews in One-Shot Federated Learning. [Paper & Code]
- Instance-wise Batch Label Restoration via Gradients in Federated Learning. [Paper & Code]
- That Label's got Style: Handling Label Style Bias for Uncertain Image Segmentation. [Paper & Code]
- Learning Hyper Label Model for Programmatic Weak Supervision. [Paper & Code]
- Rhino: Deep Causal Temporal Relationship Learning with History-dependent Noise. [Paper & Code]
Papers & Code in 2022
NeurIPS 2022
- Estimating Noise Transition Matrix with Label Correlations for Noisy Multi-Label Learning . [Paper][Code]
- Learning from Label Proportions by Learning with Label Noise. [Paper & Code]
- Class-Dependent Label-Noise Learning with Cycle-Consistency Regularization. [Paper & Code]
- On Image Segmentation With Noisy Labels: Characterization and Volume Properties of the Optimal Solutions to Accuracy and Dice. [Paper & Code]
- Robustness to Label Noise Depends on the Shape of the Noise Distribution. [Paper & Code]
- Label Noise in Adversarial Training: A Novel Perspective to Study Robust Overfitting. [Paper & Code]
- SoftPatch: Unsupervised Anomaly Detection with Noisy Data. [Paper & Code]
ECCV 2022
- Neighborhood Collective Estimation for Noisy Label Identification and Correction. [Paper][Code]
- Teaching with Soft Label Smoothing for Mitigating Noisy Labels in Facial Expressions. [Paper][Code]
- Learning from Multiple Annotator Noisy Labels via Sample-wise Label Fusion. [Paper][Code]
- Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition. [Paper][Code]
- Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels. [Paper][Code]
- Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection. [Paper][Code]
- Identifying Hard Noise in Long-Tailed Sample Distribution. [Paper][Code]
- Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalization. [Paper]
- BoundaryFace: A mining framework with noise label self-correction for Face Recognition. [Paper][Code]
- Embedding contrastive unsupervised features to cluster in- and out-of-distribution noise in corrupted image datasets. [Paper][Code]
- WeLSA: Learning To Predict 6D Pose From Weakly Labeled Data Using Shape Alignment. [Paper]
- Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsing. [Paper][Code]
- PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection. [Paper][Code]
- Active label correction using robust parameter update and entropy propagation. [Paper]
- A data-centric approach for improving ambiguous labels with combined semi-supervised classification and clustering. [Paper][Code]
ICML 2022
- [UCSC REAL Lab] To Smooth or Not? When Label Smoothing Meets Noisy Labels. [Paper][Code]
- [UCSC REAL Lab] Detecting Corrupted Labels Without Training a Model to Predict. [Paper][Code]
- [UCSC REAL Lab] Beyond Images: Label Noise Transition Matrix Estimation for Tasks with Lower-Quality Features. [Paper]
- Robust Training under Label Noise by Over-parameterization. [Paper][Code]
- Estimating Instance-dependent Label-noise Transition Matrix using DNNs. [Paper]
- Transfer and Marginalize: Explaining Away Label Noise with Privileged Information. [Paper]
- Guaranteed Robust Deep Learning against Extreme Label Noise using Self-supervised Learning.
- Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptile. [Paper][Code]
- Learning General Halfspaces with Adversarial Label Noise via Online Gradient Descent. [Paper]
- Guaranteed Robust Deep Learning against Extreme Label Noise using Self-supervised Learning.
CVPR 2022
- Selective-Supervised Contrastive Learning with Noisy Labels. [Paper][Code]
- Scalable Penalized Regression for Noise Detection in Learning with Noisy Labels. [Paper][Code]
- Large-Scale Pre-training for Person Re-identification with Noisy Labels. [Paper][Code]
- Adaptive Early-Learning Correction for Segmentation from Noisy Annotations. [Paper][Code]
ICLR 2022
- [UCSC REAL Lab] Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations. [Paper][Code]
- Resolving Training Biases via Influence-based Data Relabeling. [Paper and Code]
- Contrastive Label Disambiguation for Partial Label Learning. [Paper and Code]
- Sample Selection with Uncertainty of Losses for Learning with Noisy Labels. [Paper and Code]
- An Information Fusion Approach to Learning with Instance-Dependent Label Noise. [Paper and Code]
- Meta Discovery: Learning to Discover Novel Classes given Very Limited Data. [Paper and Code]
AISTATS 2022
- Robustness and reliability when training with noisy labels. [Paper]
- A Spectral Perspective of DNN Robustness to Label Noise.
- Hardness of Learning a Single Neuron with Adversarial Label Noise.
- Learning from Multiple Noisy Partial Labelers. [Paper]
Other Conferences 2022
ArXiv 2022
- [UCSC REAL Lab] To Aggregate or Not? Learning with Separate Noisy Labels. [Paper]
- [UCSC REAL Lab] Identifiability of Label Noise Transition Matrix. [Paper]
- Constrained Instance and Class Reweighting for Robust Learning under Label Noise. [Paper]
- AUGLOSS: A Learning Methodology for Real-World Dataset Corruption. [Paper]
- Do We Need to Penalize Variance of Losses for Learning with Label Noise?. [Paper]
- Robust Training under Label Noise by Over-parameterization. [Paper][Code]
- On Learning Contrastive Representations for Learning with Noisy Labels. [Paper]
- Learning from Label Proportions by Learning with Label Noise. [Paper]
- Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data. [Paper]
- Synergistic Network Learning and Label Correction for Noise-robust Image Classification. [Paper]
- Transfer and Marginalize: Explaining Away Label Noise with Privileged Information. [Paper]
- Convolutional Network Fabric Pruning With Label Noise. [Paper]
- Learning to Bootstrap for Combating Label Noise. [Paper]
- Learning with Neighbor Consistency for Noisy Labels. [Paper]
- Investigating Why Contrastive Learning Benefits Robustness Against Label Noise. [Paper]
- PARS: Pseudo-Label Aware Robust Sample Selection for Learning with Noisy Labels. [Paper]
- GMM Discriminant Analysis with Noisy Label for Each Class. [Paper]
- Learning with Label Noise for Image Retrieval by Selecting Interactions. [Paper]
- Two Wrongs Don't Make a Right: Combating Confirmation Bias in Learning with Label Noise. [Paper]
Papers & Code in 2021
NeurIPS 2021
Conference date: Dec, 6th -- Dec, 14th
- [UCSC REAL Lab] Can Less be More? When Increasing-to-Balancing Label Noise Rates Considered Beneficial. [Paper][Code]
- Open-set Label Noise Can Improve Robustness Against Inherent Label Noise. [Paper][Code]
- Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels. [Paper][Code]
- Understanding and Improving Early Stopping for Learning with Noisy Labels. [Paper][Code]
- How does a Neural Network's Architecture Impact its Robustness to Noisy Labels? [Paper][Code]
- FINE Samples for Learning with Noisy Labels. [Paper][Code]
- Label Noise SGD Provably Prefers Flat Global Minimizers. [Paper][Code]
- Improved Regularization and Robustness for Fine-tuning in Neural Networks. [Paper][Code]
- Instance-dependent Label-noise Learning under a Structural Causal Model. [Paper]
- Combating Noise: Semi-supervised Learning by Region Uncertainty Quantification. [Paper]
- DP-SSL: Towards Robust Semi-supervised Learning with A Few Labeled Samples. [Paper]
- Corruption Robust Active Learning. [Paper]
IJCAI 2021
- Learning Implicitly with Noisy Data in Linear Arithmetic. [Paper]
- Towards Understanding Deep Learning from Noisy Labels with Small-Loss Criterion. [Paper]
- Modeling Noisy Hierarchical Types in Fine-Grained Entity Typing: A Content-Based Weighting Approach. [Paper]
- Multi-level Generative Models for Partial Label Learning with Non-random Label Noise. [Paper]
ICML 2021
Conference date: Jul 18, 2021 -- Jul 24, 2021
- [UCSC REAL Lab] The importance of understanding instance-level noisy labels. [Paper]
- [UCSC REAL Lab] Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels. [Paper][Code]
- Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision. [Paper][Code]
- Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization. [Paper][Code]
- Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels. [Paper]
- Provably End-to-end Label-noise Learning without Anchor Points. [Paper]
- Asymmetric Loss Functions for Learning with Noisy Labels. [Paper][Code]
- Confidence Scores Make Instance-dependent Label-noise Learning Possible. [Paper]
- Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise. [Paper]
- Wasserstein Distributional Normalization For Robust Distributional Certification of Noisy Labeled Data. [Paper]
- Learning from Noisy Labels with No Change to the Training Process. [Paper]
ICLR 2021
- [UCSC REAL Lab] When Optimizing f-Divergence is Robust with Label Noise. [Paper][Code]
- [UCSC REAL Lab] Learning with Instance-Dependent Label Noise: A Sample Sieve Approach. [Paper][Code]
- Noise against noise: stochastic label noise helps combat inherent label noise. [Paper][Code]
- Learning with Feature-Dependent Label Noise: A Progressive Approach. [Paper][Code]
- Robust early-learning: Hindering the memorization of noisy labels. [Paper][Code]
- MoPro: Webly Supervised Learning with Momentum Prototypes. [Paper] [Code]
- Robust Curriculum Learning: from clean label detection to noisy label self-correction. [Paper]
- How Does Mixup Help With Robustness and Generalization? [Paper]
- Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data. [Paper]
CVPR 2021
Conference date: Jun 19, 2021 -- Jun 25, 2021
- [UCSC REAL Lab] A Second-Order Approach to Learning with Instance-Dependent Label Noise. [Paper][Code]
- Improving Unsupervised Image Clustering With Robust Learning. [Paper]
- Multi-Objective Interpolation Training for Robustness to Label Noise. [Paper][Code]
- Noise-resistant Deep Metric Learning with Ranking-based Instance Selection. [Paper][Code]
- Augmentation Strategies for Learning with Noisy Labels. [Paper][Code]
- Jo-SRC: A Contrastive Approach for Combating Noisy Labels. [Paper][Code]
- Multi-Objective Interpolation Training for Robustness to Label Noise. [Paper][Code]
- Partially View-aligned Representation Learning with Noise-robust Contrastive Loss. [Paper][Code]
- Correlated Input-Dependent Label Noise in Large-Scale Image Classification. [Paper]
- DAT: Training Deep Networks Robust To Label-Noise by Matching the Feature Distributions.[Paper]
- Faster Meta Update Strategy for Noise-Robust Deep Learning. [Paper][Code]
- DualGraph: A graph-based method for reasoning about label noise. [Paper]
- Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation. [Paper]
- Joint Negative and Positive Learning for Noisy Labels. [Paper]
- Faster Meta Update Strategy for Noise-Robust Deep Learning. [Paper]
- AutoDO: Robust AutoAugment for Biased Data with Label Noise via Scalable Probabilistic Implicit Differentiation. [Paper][Code]
- Meta Pseudo Labels. [Paper][Code]
- All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training. [Paper][Code]
- SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classification. [Paper][Code]
AISTATS 2021
Conference date: Apr 13, 2021 -- Apr 15, 2021
- Collaborative Classification from Noisy Labels. [Paper]
- Linear Models are Robust Optimal Under Strategic Behavior. [Paper]
AAAI 2021
- Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise. [Paper][Code]
- Learning to Purify Noisy Labels via Meta Soft Label Corrector. [Paper][Code]
- Robustness of Accuracy Metric and its Inspirations in Learning with Noisy Labels. [Paper][Code]
- Learning from Noisy Labels with Complementary Loss Functions. [Paper][Code]
- Analysing the Noise Model Error for Realistic Noisy Label Data. [Paper][Code]
- Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model. [Paper]
- Learning with Group Noise. [Paper]
- Meta Label Correction for Noisy Label Learning. [Paper]
Other Conferences 2021
- (ICCV 2021) Learning with Noisy Labels for Robust Point Cloud Segmentation. [Paper][Code]
- (ICCV 2021) Learning with Noisy Labels via Sparse Regularization. [Paper]
- (WACV 2022) Towards a Robust Differentiable Architecture Search under Label Noise. [Paper]
- (WACV 2022) Addressing out-of-distribution label noise in webly-labelled data. [Paper][Code]
- (BMVC 2021) PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labels. [Paper][Code]
- (IJCAI2021 Workshop) An Ensemble Noise-Robust K-fold Cross-Validation Selection Method for Noisy Labels. [Paper]
ArXiv 2021
- [UCSC REAL Lab] Understanding Generalized Label Smoothing when Learning with Noisy Labels. [Paper]
- [UCSC REAL Lab] A Good Representation Detects Noisy Labels. [Paper]
- [UCSC REAL Lab] Demystifying How Self-Supervised Features Improve Training from Noisy Labels. [Paper][code]
- Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks. [Paper][Code]
- Double Descent in Adversarial Training: An Implicit Label Noise Perspective. [Paper]
- Estimating Instance-dependent Label-noise Transition Matrix using DNNs. [Paper]
- A Theoretical Analysis of Learning with Noisily Labeled Data. [Paper]
- Learning from Multiple Annotators by Incorporating Instance Features. [Paper]
- Learning from Multiple Noisy Partial Labelers. [Paper]
- Instance Correction for Learning with Open-set Noisy Labels. [Paper]
- Sample Selection with Uncertainty of Losses for Learning with Noisy Labels. [Paper]
- Analysis of classifiers robust to noisy labels. [Paper]
- NoiLIn: Do Noisy Labels Always Hurt Adversarial Training? [Paper]
- Alleviating Noisy-label Effects in Image Classification via Probability Transition Matrix. [Paper]
- Learning with Noisy Labels by Targeted Relabeling. [Paper]
- Simple Attention Module based Speaker Verification with Iterative noisy label detection. [Paper]
- Adaptive Early-Learning Correction for Segmentation from Noisy Annotations. [Paper]
- Robust Deep Learning from Crowds with Belief Propagation. [Paper]
- Adaptive Hierarchical Similarity Metric Learning with Noisy Labels. [Paper]
- Prototypical Classifier for Robust Class-Imbalanced Learning. [Paper]
- A Survey of Label-noise Representation Learning: Past, Present and Future. [Paper]
- Noisy-Labeled NER with Confidence Estimation. [Paper][Code]
- Study Group Learning: Improving Retinal Vessel Segmentation Trained with Noisy Labels. [Paper][Code]
- Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels. [Paper][Code]
- Exponentiated Gradient Reweighting for Robust Training Under Label Noise and Beyond. [Paper]
- Understanding the Interaction of Adversarial Training with Noisy Labels. [Paper]
- Learning from Noisy Labels via Dynamic Loss Thresholding. [Paper]
- Evaluating Multi-label Classifiers with Noisy Labels. [Paper]
- Self-Supervised Noisy Label Learning for Source-Free Unsupervised Domain Adaptation. [Paper]
- Transform consistency for learning with noisy labels. [Paper]
- Learning to Combat Noisy Labels via Classification Margins. [Paper]
- Joint Negative and Positive Learning for Noisy Labels. [Paper]
- Robust Classification from Noisy Labels: Integrating Additional Knowledge for Chest Radiography Abnormality Assessment. [Paper]
- DST: Data Selection and joint Training for Learning with Noisy Labels. [Paper]
- LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environment. [Paper]
- A Novel Perspective for Positive-Unlabeled Learning via Noisy Labels. [Paper]
- Ensemble Learning with Manifold-Based Data Splitting for Noisy Label Correction. [Paper]
- MetaLabelNet: Learning to Generate Soft-Labels from Noisy-Labels. [Paper]
- On the Robustness of Monte Carlo Dropout Trained with Noisy Labels. [Paper]
- Co-matching: Combating Noisy Labels by Augmentation Anchoring. [Paper]
- Pathological Image Segmentation with Noisy Labels. [Paper]
- CrowdTeacher: Robust Co-teaching with Noisy Answers & Sample-specific Perturbations for Tabular Data. [Paper]
- Approximating Instance-Dependent Noise via Instance-Confidence Embedding. [Paper]
- Rethinking Noisy Label Models: Labeler-Dependent Noise with Adversarial Awareness. [Paper]
- ScanMix: Learning from Severe Label Noise viaSemantic Clustering and Semi-Supervised Learning. [Paper]
- Friends and Foes in Learning from Noisy Labels. [Paper]
- Learning from Noisy Labels for Entity-Centric Information Extraction. [Paper]
- A Fremework Using Contrastive Learning for Classification with Noisy Labels. [Paper]
- Contrastive Learning Improves Model Robustness Under Label Noise. [Paper][Code]
- Noise-Resistant Deep Metric Learning with Probabilistic Instance Filtering. [Paper]
- Compensation Learning. [Paper]
- kNet: A Deep kNN Network To Handle Label Noise. [Paper]
- Temporal-aware Language Representation Learning From Crowdsourced Labels. [Paper]
- Memorization in Deep Neural Networks: Does the Loss Function matter?. [Paper]
- Mitigating Memorization in Sample Selection for Learning with Noisy Labels. [Paper]
- P-DIFF: Learning Classifier with Noisy Labels based on Probability Difference Distributions. [Paper][Code]
- Decoupling Representation and Classifier for Noisy Label Learning. [Paper]
- Contrastive Representations for Label Noise Require Fine-Tuning. [Paper]
- NGC: A Unified Framework for Learning with Open-World Noisy Data. [Paper]
- Learning From Long-Tailed Data With Noisy Labels. [Paper]
- Robust Long-Tailed Learning Under Label Noise. [Paper]
- Instance-dependent Label-noise Learning under a Structural Causal Model. [Paper]
- Assessing the Quality of the Datasets by Identifying Mislabeled Samples. [Paper]
- Learning to Aggregate and Refine Noisy Labels for Visual Sentiment Analysis. [Paper]
- Robust Temporal Ensembling for Learning with Noisy Labels. [Paper]
- Knowledge Distillation with Noisy Labels for Natural Language Understanding. [Paper]
- Robustness and reliability when training with noisy labels. [Paper]
- Noisy Annotations Robust Consensual Collaborative Affect Expression Recognition. [Paper]
- Consistency Regularization Can Improve Robustness to Label Noise. [Paper]
Papers & Code in 2020
ICML 2020
- [UCSC REAL Lab] Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates. [Paper][Code 1] [Code 2]
- Normalized Loss Functions for Deep Learning with Noisy Labels. [Paper][Code]
- SIGUA: Forgetting May Make Learning with Noisy Labels More Robust. [Paper][Code]
- Error-Bounded Correction of Noisy Labels. [Paper][Code]
- Training Binary Neural Networks through Learning with Noisy Supervision. [Paper][Code]
- Improving generalization by controlling label-noise information in neural network weights. [Paper][Code]
- Self-PU: Self Boosted and Calibrated Positive-Unlabeled Training. [Paper][Code]
- Searching to Exploit Memorization Effect in Learning with Noisy Labels. [Paper][Code]
- Learning with Bounded Instance and Label-dependent Label Noise. [Paper]
- Label-Noise Robust Domain Adaptation. [Paper]
- Beyond Synthetic Noise: Deep Learning on Controlled Noisy Labels. [Paper]
- Does label smoothing mitigate label noise?. [Paper]
- Learning with Multiple Complementary Labels. [Paper]
- Deep k-NN for Noisy Labels. [Paper]
- Extreme Multi-label Classification from Aggregated Labels. [Paper]
ICLR 2020
- DivideMix: Learning with Noisy Labels as Semi-supervised Learning. [Paper][Code]
- Learning from Rules Generalizing Labeled Exemplars. [Paper] [Code]
- Robust training with ensemble consensus. [Paper][Code]
- Self-labelling via simultaneous clustering and representation learning. [Paper][Code]
- Can gradient clipping mitigate label noise? [Paper][Code]
- Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification. [Paper][Code]
- Curriculum Loss: Robust Learning and Generalization against Label Corruption. [Paper]
- Simple and Effective Regularization Methods for Training on Noisily Labeled Data with Generalization Guarantee. [Paper]
- SELF: Learning to Filter Noisy Labels with Self-Ensembling. [Paper]
Nips 2020
- Part-dependent Label Noise: Towards Instance-dependent Label Noise. [Paper][Code]
- Identifying Mislabeled Data using the Area Under the Margin Ranking. [Paper][Code]
- Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning. [Paper]
- Early-Learning Regularization Prevents Memorization of Noisy Labels. [Paper][Code]
- Coresets for Robust Training of Deep Neural Networks against Noisy Labels. [Paper][Code]
- Modeling Noisy Annotations for Crowd Counting. [Paper][Code]
- Robust Optimization for Fairness with Noisy Protected Groups. [Paper][Code]
- Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping. [Paper][Code]
- A Topological Filter for Learning with Label Noise. [Paper][Code]
- Self-Adaptive Training: beyond Empirical Risk Minimization. [Paper][Code]
- Disentangling Human Error from the Ground Truth in Segmentation of Medical Images. [Paper][Code]
- Non-Convex SGD Learns Halfspaces with Adversarial Label Noise. [Paper]
- Efficient active learning of sparse halfspaces with arbitrary bounded noise. [Paper]
- Semi-Supervised Partial Label Learning via Confidence-Rated Margin Maximization. [Paper]
- Labelling unlabelled videos from scratch with multi-modal self-supervision. [Paper][Code]
- Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning. [Paper][Code]
- MetaPoison: Practical General-purpose Clean-label Data Poisoning. [Paper][Code 1][Code 2]
- Provably Consistent Partial-Label Learning. [Paper]
- A Variational Approach for Learning from Positive and Unlabeled Data. [Paper][Code]
AAAI 2020
- [UCSC REAL Lab] Reinforcement Learning with Perturbed Rewards. [Paper] [Code]
- Less Is Better: Unweighted Data Subsampling via Influence Function. [Paper] [Code]
- Weakly Supervised Sequence Tagging from Noisy Rules. [Paper][Code]
- Coupled-View Deep Classifier Learning from Multiple Noisy Annotators. [Paper]
- Partial multi-label learning with noisy label identification. [Paper]
- Self-Paced Robust Learning for Leveraging Clean Labels in Noisy Data. [Paper]
- Label Error Correction and Generation Through Label Relationships. [Paper]
CVPR 2020
- Combating noisy labels by agreement: A joint training method with co-regularization. [Paper][Code]
- Distilling Effective Supervision From Severe Label Noise. [Paper][Code]
- Self-Training With Noisy Student Improves ImageNet Classification. [Paper][Code]
- Noise Robust Generative Adversarial Networks. [Paper][Code]
- Global-Local GCN: Large-Scale Label Noise Cleansing for Face Recognition. [Paper]
- DLWL: Improving Detection for Lowshot Classes With Weakly Labelled Data. [Paper]
- Spherical Space Domain Adaptation With Robust Pseudo-Label Loss. [Paper][Code]
- Training Noise-Robust Deep Neural Networks via Meta-Learning. [Paper][Code]
- Shoestring: Graph-Based Semi-Supervised Classification With Severely Limited Labeled Data. [Paper][Code]
- Noise-Aware Fully Webly Supervised Object Detection. [Paper][Code]
- Learning From Noisy Anchors for One-Stage Object Detection. [Paper][Code]
- Generating Accurate Pseudo-Labels in Semi-Supervised Learning and Avoiding Overconfident Predictions via Hermite Polynomial Activations. [Paper][Code]
- Revisiting Knowledge Distillation via Label Smoothing Regularization. [Paper][Code]
ECCV 2020
- 2020-ECCV - Learning with Noisy Class Labels for Instance Segmentation. [Paper][Code]
- 2020-ECCV - Suppressing Mislabeled Data via Grouping and Self-Attention. [Paper][Code]
- 2020-ECCV - NoiseRank: Unsupervised Label Noise Reduction with Dependence Models. [Paper]
- 2020-ECCV - Weakly Supervised Learning with Side Information for Noisy Labeled Images. [Paper]
- 2020-ECCV - Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection. [Paper]
- 2020-ECCV - Graph convolutional networks for learning with few clean and many noisy labels. [Paper]
ArXiv 2020
- No Regret Sample Selection with Noisy Labels. [Paper][Code]
- Meta Soft Label Generation for Noisy Labels. [Paper][Code]
- Learning from Noisy Labels with Deep Neural Networks: A Survey. [Paper]
- RAR-U-Net: a Residual Encoder to Attention Decoder by Residual Connections Framework for Spine Segmentation under Noisy Labels. [Paper]
- Learning from Small Amount of Medical Data with Noisy Labels: A Meta-Learning Approach. [Paper]
Hyperspectral Image Denoising
Deep Learning Methods
-
Hyperspectral Imagery Denoising by Deep Learning With Trainable Nonlinearity Function, GRSL 2017, Weiying Xie et al.[Page]
-
[HSI-DeNet]: Hyperspectral Image Restoration via Convolutional Neural Network, IEEE TGRS 2018, Yi Chang et al.[Page][Web][Pdf]
-
[HSID-CNN]:Hyperspectral Image Denoising Employing a Spatial-Spectral Deep Residual Convolutional Neural Network, IEEE TGRS 2018, Qiangqiang Yuan et al.[Page][Code]
-
[Deep Hyperspectral Prior]: Denoising, Inpainting, Super-Resolution, ICCV Workshops 2019, Oleksii Sidorov et al.[Page][Code] [Pdf]
-
A 3-D Atrous Convolution Neural Network for Hyperspectral Image Denoising, IEEE TGRS 2019, Wei Liu et al.[Page]
-
Hybrid Noise Removal in Hyperspectral Imagery With a Spatial-Spectral Gradient Network, IEEE TGRS 2019, Qiang Zhang et al.[Page][Code][Pdf]
-
Deep Spatial-spectral Representation Learning for Hyperspectral Image Denoising, IEEE TCI 2019, Weisheng Dong et al. [Page] [Code]
-
Zero-Shot Hyperspectral Image Denoising With Separable Image Prior, ICCV Workshops 2019, Ryuji Imamura et al.[Page]
-
Source:Self-supervised Hyperspectral Image Restoration using Separable Image Prior, arxiv 2019, Ryuji Imamura et al.[Page]
-
DNN-based Hyperspectral Image Denoising with Spatio-spectral Pre-training, IEEE GCCE 2019, Tatsuki Itasaka et al.[Page]
-
Efficient Convolutional Neural Network for Spectral-Spatial Hyperspectral Denoising, WHISPERS 2019, Alessandro Maffei et al.[Page]
2020
-
[HSI-SDeCNN]:A Single Model CNN for Hyperspectral, IEEE TGRS 2020 , Alessandro Maffei et al.[Page][Pdf][Code]
-
3-D Quasi-Recurrent Neural Network for Hyperspectral Image Denoising, IEEE TNNLS 2020, Kaixuan Wei et al.[Page][Code][Pdf]
-
Hyperspectral Image Denoising Using SURE-Based Unsupervised Convolutional Neural Networks, IEEE TGRS 2020 , Han V. Nguyen et al.[Page]
-
ADRN: Attention-based deep residual network for hyperspectral image denoising, ICASSP 2020 , Yongsen Zhao et al.[Page][Pdf]
-
A New Multiscale Residual Learning Network for HSI Inconsistent Noise Removal, GRSL 2020 , Yuan Yuan et al.[Page]
-
A Comprehensive Comparison of Multi-Dimensional Image Denoising Methods, arxiv 2020 , Zhaoming Kong et al.[Page]
2021
-
Hyperspectral Image Denoising Using a 3-D Attention Denoising Network, TGRS 2021 , Qian Shi et al.[Page]
-
Hyperspectral Image Denoising Based On Multi-Stream Denoising Network, IGARSS 2021 , Yan Gao et al.[Page]
-
A Self-Supervised Denoising Network for Satellite-Airborne-Ground Hyperspectral Imagery, TGRS 2021 , Xinyu Wang et al.[Page]
-
Partial-DNet: A Novel Blind Denoising Model With Noise Intensity Estimation for HSI, TGRS 2021 , Yuan Yuan et al.[Page]
-
Deep Spatial-Spectral Global Reasoning Network for Hyperspectral Image Denoising, TGRS 2021 , Xiangyong Cao et al.[Page][Code]
-
Attention-Based Octave Network for Hyperspectral Image Denoising, JSTARS 2021 , Ziwen Kan et al.[Page][Code]
-
SSCAN: A Spatial-spectral Cross Attention Network for Hyperspectral Image Denoising, arxiv 2021 , Zhiqiang Wang et al.[Page]
-
Hyperspectral Image Restoration with Self-supervised Learning: A Two-stage Training Approach, TGRS 2021 , Yuntao Qian et al.[Page]
2022
-
DnRCNN: Deep Recurrent Convolutional Neural Network for HSI Destriping, TNNLS 2022 , Juntao Guan et al.[Page]
-
Toward Real Hyperspectral Image Stripe Removal via Direction Constraint Hierarchical Feature Cascade Networks, RS 2022 , Chengjun Wang et al.[Page]
-
Deep plug-and-play prior for hyperspectral image restoration, Neurocomputing 2022 , Zeqiang Lai et al.[Page]
Hybrid models
- Hyperspectral Image Denoising via Matrix Factorization and Deep Prior Regularization, IEEE TIP 2019, Baihong Lin et al[Page]
- Hyperspectral image restoration via CNN denoiser prior regularized low-rank tensor recovery, CVIU 2020, H. Zeng et al..[Page]
- Deep spatio-spectral Bayesian posterior for hyperspectral image non-i.i.d. noise removal, ISPRS JPRS 2020, Qiang Zhang et al.[Page][Pdf]
- SMDS-Net: Model Guided Spectral-Spatial Network for Hyperspectral Image Denoising, arXiv 2020 , Fengchao Xiong et al.[Page]
- Unsupervised Hyperspectral Mixed Noise Removal Via Spatial-Spectral Constrained Deep Image Prior, arxiv 2020, Yi-Si Luo et al.[Page]
- Hyperspectral Mixed Noise Removal via Spatial-Spectral Constrained Unsupervised Deep Image Prior, JSTARS 2021 , Yi-Si Luo et al.[Page]
- Hyperspectral Image Denoising via Clustering-Based Latent Variable in Variational Bayesian Framework, TGRS 2021, Peyman Azimpour et al.[Page]
- Hyperspectral Denoising Via Global Tensor Ring Decomposition and Local Unsupervised Deep Image Prior, IGARSS 2021 , Jian-Li Wang et al.[Page]
- Learning a Model-Based Deep Hyperspectral Denoiser from a Single Noisy Hyperspectral Image, IGARSS 2021 , Guanyiman Fu et al.[Page]
- Hyperspectral Denoising Using Unsupervised Disentangled Spatiospectral Deep Priors, TGRS 2021 , Yu-Chun Miao et al.[Page]
- LR-Net: Low-Rank Spatial-Spectral Network for Hyperspectral Image Denoising, TIP 2021 , Hongyan Zhang et al.[Page]
- A Trainable Spectral-Spatial Sparse Coding Model for Hyperspectral Image Restoration, NeurIPS 2021 , Theo Bodrito et al.[Page][Code]
- MAC-Net: Model Aided Nonlocal Neural Network for Hyperspectral Image Denoising, TGRS 2021 , Fengchao Xiong et al.[Page]
- Hyperspectral Image Mixed Noise Removal Using Subspace Representation and Deep CNN Image Prior, RS 2021 , Lina Zhuang et al.[Page]
- Hyperspectral Image Denoising via Low-Rank Representation and CNN Denoiser, JSTARS 2021 , Hezhi Sun et al.[Page]
- FastHyMix: Fast and Parameter-Free Hyperspectral Image Mixed Noise Removal, TNNLS 2021 , Lina Zhuang et al.[Page][Code]
Temporarily uncategorized
- Evolving Deep Convolutional Neural Networks for Hyperspectral Image Denoising, IJCNN 2020 , Yuqiao Liu et al.[Page]
- A novel fusion paradigm for multi-channel image denoising, Information Fusion 2020 , Yue Wu et al.[Page]
Other tasks
- HSI-IPNet: Hyperspectral Imagery Inpainting by Deep Learning With Adaptive Spectral Extraction, IEEE J-STARS 2020, Rong Wong et al.[Page][Pdf]
- Fast stripe noise removal from hyperspectral image via multi-scale dilated unidirectional convolution, Multimedia Tools and Applications 2020, Ziying Wang et al.[Page][Code]
- Toward Universal Stripe Removal via Wavelet-Based Deep Convolutional Neural Network, IEEE TGRS 2020, Yi Chang et al.[Page]
- Learning Spectral-Spatial Prior Via 3DDNCNN for Hyperspectral Image Deconvolution, ICASSP 2020, Xiuheng Wang et al.[Page]
- DnRCNN: Deep Recurrent Convolutional Neural Network for HSI Destriping, TNNLS 2022 , Juntao Guan et al.[Page]
Reconstruction
- Hyperspectral Image Reconstruction Using a Deep Spatial-Spectral Prior, CVPR 2019 , Lizhi Wang et al.[Page][Pdf]
- HyperMixNet: Hyperspectral Image Reconstruction With Deep Mixed Network From a Snapshot Measurement, ICCV Workshops 2021 , Kouhei Yorimoto et al.[Page]
Extra
- Deep learning on image denoising: An overview, Neural Networks 2020, Chunwei Tian et al.[Page]
- A Comprehensive Comparison of Multi-Dimensional Image Denoising Methods, arxiv 2020, Zhaoming Kong et al.[Page]
- Hyperspectral Image Denoising with Realistic Data, ICCV 2021 , Tao Zhang et al.[Page][Code]
- Image Restoration for Remote Sensing: Overview and Toolbox, arxiv 2021, Benhood Rasti et al.[Page][Code]
- HyDe: The First Open-Source, Python-Based, GPU-Accelerated Hyperspectral Denoising Package, arxiv 2022, Daniel Coquelin et al.[Page][Code]
Datasets
- CAVE dataset
- Harvard dataset
- ICVL dataset
- AVIRIS
- ROSIS
- HYDICE
- EO-1 Hyperion Data
- NUS dataset
- NTIRE18 dataset
Image Quality Measurement
- Peak Signal to Noise Ratio (PSNR)
- Structural SIMilarity index (SSIM)
- Spectral Angle Mapper (SAM)
- Erreur Relative Globale Adimensionnelle de Synthèse (ERGAS)
- Feature SIMilarity index (FSIM)