TPAMI 2023 papers on Label-efficient and robust learning
121 of the 664 papers published in TPAMI 2023 (18.2%) are on Label-efficient and robust learning, compared with 17.8% at TPAMI 2022. They fall into 8 topics.
See TPAMI 2023 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Recognition and long-tail · 46 papers
- Deep Long-Tailed Learning: A Survey (960 citations)
- Channel Augmentation for Visible-Infrared Re-Identification (106 citations)
- Brain-Machine Coupled Learning Method for Facial Emotion Recognition (85 citations)
- Generalized Parametric Contrastive Learning (82 citations)
- The Importance of Expert Knowledge for Automatic Modulation Open Set Recognition (55 citations)
- Attribute-Aware Deep Hashing With Self-Consistency for Large-Scale Fine-Grained Image Retrieval (50 citations)
- Towards Enabling Binary Decomposition for Partial Multi-Label Learning (45 citations)
- Introspective Deep Metric Learning (41 citations)
- Attribute-Guided Collaborative Learning for Partial Person Re-Identification (40 citations)
- Weakly Supervised Tracklet Association Learning With Video Labels for Person Re-Identification (39 citations)
- SketchTrans: Disentangled Prototype Learning With Transformer for Sketch-Photo Recognition (38 citations)
- Positive-Unlabeled Learning With Label Distribution Alignment (32 citations)
and 34 more in the interactive map.
Domain adaptation and generalization · 16 papers
- SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation (234 citations)
- Self-Adversarial Disentangling for Specific Domain Adaptation (67 citations)
- ADPL: Adaptive Dual Path Learning for Domain Adaptation of Semantic Segmentation (58 citations)
- Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentation (58 citations)
- Digging Into Uncertainty-Based Pseudo-Label for Robust Stereo Matching (55 citations)
- Source-Free Progressive Graph Learning for Open-Set Domain Adaptation (40 citations)
- MMT: Cross Domain Few-Shot Learning via Meta-Memory Transfer (31 citations)
- AUC-Oriented Domain Adaptation: From Theory to Algorithm (23 citations)
- Trust Your Good Friends: Source-Free Domain Adaptation by Reciprocal Neighborhood Clustering (21 citations)
- Evolving Domain Generalization via Latent Structure-Aware Sequential Autoencoder (17 citations)
- MADAv2: Advanced Multi-Anchor Based Active Domain Adaptation Segmentation (16 citations)
- Handling Open-Set Noise and Novel Target Recognition in Domain Adaptive Semantic Segmentation (15 citations)
and 4 more in the interactive map.
Zero-/few-shot and meta-learning · 15 papers
- LibFewShot: A Comprehensive Library for Few-Shot Learning (101 citations)
- Dual Adaptive Representation Alignment for Cross-Domain Few-Shot Learning (63 citations)
- Learning to Learn Task-Adaptive Hyperparameters for Few-Shot Learning (63 citations)
- Generative Multi-Label Zero-Shot Learning (58 citations)
- From Instance to Metric Calibration: A Unified Framework for Open-World Few-Shot Learning (35 citations)
- Prototype Completion for Few-Shot Learning (27 citations)
- Reconstruction Guided Meta-Learning for Few Shot Open Set Recognition (27 citations)
- Simple Primitives With Feasibility- and Contextuality-Dependence for Open-World Compositional Zero-Shot Learning (26 citations)
- No Adversaries to Zero-Shot Learning: Distilling an Ensemble of Gaussian Feature Generators (22 citations)
- Explanatory Object Part Aggregation for Zero-Shot Learning (18 citations)
- Clustered Task-Aware Meta-Learning by Learning From Learning Paths (13 citations)
- Contextualizing Meta-Learning via Learning to Decompose (11 citations)
and 3 more in the interactive map.
Semi-supervised learning · 12 papers
- A Survey of Vectorization Methods in Topological Data Analysis (113 citations)
- Querying Labeled for Unlabeled: Cross-Image Semantic Consistency Guided Semi-Supervised Semantic Segmentation (105 citations)
- PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning (90 citations)
- SS-TBN: A Semi-Supervised Tri-Branch Network for COVID-19 Screening and Lesion Segmentation (61 citations)
- Semi-Supervised Learning for Multi-Label Cardiovascular Diseases Prediction: A Multi-Dataset Study (44 citations)
- Source Free Semi-Supervised Transfer Learning for Diagnosis of Mental Disorders on fMRI Scans (38 citations)
- Negatives Make a Positive: An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning (31 citations)
- BAL: Balancing Diversity and Novelty for Active Learning (26 citations)
- Underground Diagnosis Based on GPR and Learning in the Model Space (18 citations)
- Rewarded Semi-Supervised Re-Identification on Identities Rarely Crossing Camera Views (14 citations)
- Supervision by Denoising (14 citations)
- Semi-Supervised Learning for FGVC With Out-of-Category Data (11 citations)
Self-supervised and contrastive · 10 papers
- Contrastive Masked Autoencoders are Stronger Vision Learners (234 citations)
- SignBERT+: Hand-Model-Aware Self-Supervised Pre-Training for Sign Language Understanding (170 citations)
- A Unified Visual Information Preservation Framework for Self-supervised Pre-training in Medical Image Analysis (90 citations)
- Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning (64 citations)
- Learning Gait Representation From Massive Unlabelled Walking Videos: A Benchmark (63 citations)
- CaCo: Both Positive and Negative Samples are Directly Learnable via Cooperative-Adversarial Contrastive Learning (31 citations)
- Unsupervised Deraining: Where Asymmetric Contrastive Learning Meets Self-Similarity (31 citations)
- High-Order Correlation-Guided Slide-Level Histology Retrieval With Self-Supervised Hashing (19 citations)
- SERE: Exploring Feature Self-Relation for Self-Supervised Transformer (19 citations)
- Development of Few-Shot Learning Capabilities in Artificial Neural Networks When Learning Through Self-Supervised Interaction
Knowledge distillation · 8 papers
- Dataset Distillation: A Comprehensive Review (210 citations)
- When Object Detection Meets Knowledge Distillation: A Survey (206 citations)
- A Comprehensive Survey of Dataset Distillation (156 citations)
- Online Knowledge Distillation via Mutual Contrastive Learning for Visual Recognition (119 citations)
- Localization Distillation for Object Detection (114 citations)
- Structured Knowledge Distillation for Accurate and Efficient Object Detection (66 citations)
- SimSwap++: Towards Faster and High-Quality Identity Swapping (37 citations)
- Teach-DETR: Better Training DETR With Teachers (17 citations)
Noisy labels · 8 papers
- Asymmetric Loss Functions for Noise-Tolerant Learning: Theory and Applications (86 citations)
- CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning (72 citations)
- Regularly Truncated M-Estimators for Learning With Noisy Labels (23 citations)
- Knockoffs-SPR: Clean Sample Selection in Learning With Noisy Labels (18 citations)
- Dynamic Loss for Robust Learning (16 citations)
- A Parametrical Model for Instance-Dependent Label Noise (14 citations)
- Latent Class-Conditional Noise Model (9 citations)
- Noisy Label Learning With Provable Consistency for a Wider Family of Losses (5 citations)
OOD and anomaly detection · 6 papers
- Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection (135 citations)
- Revisiting Confidence Estimation: Towards Reliable Failure Prediction (34 citations)
- General Greedy De-Bias Learning (30 citations)
- WOOD: Wasserstein-Based Out-of-Distribution Detection (21 citations)
- Adversarial Data Augmentation for HMM-Based Anomaly Detection (17 citations)
- Supervision Adaptation Balancing In-Distribution Generalization and Out-of-Distribution Detection (11 citations)
