TPAMI 2024 papers on Label-efficient and robust learning
104 of the 666 papers published in TPAMI 2024 (15.6%) are on Label-efficient and robust learning, compared with 18.2% at TPAMI 2023. They fall into 9 topics.
See TPAMI 2024 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 · 36 papers
- End-to-End Autonomous Driving: Challenges and Frontiers (848 citations)
- Disentangled Representation Learning (284 citations)
- From Simple to Complex Scenes: Learning Robust Feature Representations for Accurate Human Parsing (140 citations)
- A Survey on Information Bottleneck (138 citations)
- Synthetic Data in Human Analysis: A Survey (128 citations)
- Does Negative Sampling Matter? a Review With Insights Into its Theory and Applications (68 citations)
- IG 2 : Integrated Gradient on Iterative Gradient Path for Feature Attribution (47 citations)
- Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces (37 citations)
- Many-Objective Jaccard-Based Evolutionary Feature Selection for High-Dimensional Imbalanced Data Classification (30 citations)
- NineRec: A Benchmark Dataset Suite for Evaluating Transferable Recommendation (29 citations)
- FLAC: Fairness-Aware Representation Learning by Suppressing Attribute-Class Associations (26 citations)
- A Versatile Framework for Multi-Scene Person Re-Identification (25 citations)
and 24 more in the interactive map.
Domain adaptation and generalization · 16 papers
- A Comprehensive Survey on Source-Free Domain Adaptation (323 citations)
- Behind Every Domain There is a Shift: Adapting Distortion-Aware Vision Transformers for Panoramic Semantic Segmentation (56 citations)
- Source-Free Domain Adaptation With Domain Generalized Pretraining for Face Anti-Spoofing (46 citations)
- A Curriculum-Style Self-Training Approach for Source-Free Semantic Segmentation (40 citations)
- Gradient Harmonization in Unsupervised Domain Adaptation (28 citations)
- Evidential Multi-Source-Free Unsupervised Domain Adaptation (25 citations)
- 360SFUDA++: Towards Source-Free UDA for Panoramic Segmentation by Learning Reliable Category Prototypes (18 citations)
- One Fits Many: Class Confusion Loss for Versatile Domain Adaptation (18 citations)
- PnP-GA+: Plug-and-Play Domain Adaptation for Gaze Estimation Using Model Variants (14 citations)
- Anti-Forgetting Adaptation for Unsupervised Person Re-Identification (13 citations)
- Geometric Understanding of Discriminability and Transferability for Visual Domain Adaptation (13 citations)
- Adaptive Graph Learning With Semantic Promotability for Domain Adaptation (11 citations)
and 4 more in the interactive map.
Noisy labels · 11 papers
- A Two-Stage Noise-Tolerant Paradigm for Label Corrupted Person Re-Identification (53 citations)
- BadLabel: A Robust Perspective on Evaluating and Enhancing Label-Noise Learning (45 citations)
- NICEST: Noisy Label Correction and Training for Robust Scene Graph Generation (43 citations)
- Tackling Noisy Labels With Network Parameter Additive Decomposition (24 citations)
- Searching to Exploit Memorization Effect in Deep Learning With Noisy Labels (19 citations)
- Transferring Annotator- and Instance-Dependent Transition Matrix for Learning From Crowds (18 citations)
- A Time-Consistency Curriculum for Learning From Instance-Dependent Noisy Labels (13 citations)
- ELDP: Enhanced Label Distribution Propagation for Crowdsourcing (12 citations)
- Estimating Per-Class Statistics for Label Noise Learning (11 citations)
- Adaptive Learning for Dynamic Features and Noisy Labels (6 citations)
- Student Loss: Towards the Probability Assumption in Inaccurate Supervision
Zero-/few-shot and meta-learning · 10 papers
- Advances and Challenges in Meta-Learning: A Technical Review (372 citations)
- Content-Aware Rectified Activation for Zero-Shot Fine-Grained Image Retrieval (47 citations)
- Bi-Directional Ensemble Feature Reconstruction Network for Few-Shot Fine-Grained Classification (41 citations)
- Learning From Human Attention for Attribute-Assisted Visual Recognition (23 citations)
- Disentangling Before Composing: Learning Invariant Disentangled Features for Compositional Zero-Shot Learning (18 citations)
- Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification (15 citations)
- PSVMA+: Exploring Multi-Granularity Semantic-Visual Adaption for Generalized Zero-Shot Learning (13 citations)
- Learning to Sketch: A Neural Approach to Item Frequency Estimation in Streaming Data (12 citations)
- Understanding Episode Hardness in Few-Shot Learning (6 citations)
- Relational Proxies: Fine-Grained Relationships as Zero-Shot Discriminators (3 citations)
Self-supervised and contrastive · 9 papers
- A Survey on Self-Supervised Learning: Algorithms, Applications, and Future Trends (756 citations)
- Self-Supervised Multimodal Learning: A Survey (167 citations)
- Weak Augmentation Guided Relational Self-Supervised Learning (79 citations)
- Inductive State-Relabeling Adversarial Active Learning With Heuristic Clique Rescaling (32 citations)
- Unveiling the Power of Self-Supervision for Multi-View Multi-Human Association and Tracking (27 citations)
- UniMiSS+: Universal Medical Self-Supervised Learning From Cross-Dimensional Unpaired Data (16 citations)
- MVEB: Self-Supervised Learning With Multi-View Entropy Bottleneck (15 citations)
- Training Networks in Null Space of Feature Covariance With Self-Supervision for Incremental Learning (6 citations)
- Understanding Whitening Loss in Self-Supervised Learning
Semi-supervised learning · 9 papers
- Probabilistic Contrastive Learning for Long-Tailed Visual Recognition (127 citations)
- Mine yOur owN Anatomy: Revisiting Medical Image Segmentation With Extremely Limited Labels (117 citations)
- Virtual Category Learning: A Semi-Supervised Learning Method for Dense Prediction With Extremely Limited Labels (94 citations)
- Robust Semi-Supervised Learning by Wisely Leveraging Open-Set Data (23 citations)
- Semi-Supervised Coupled Thin-Plate Spline Model for Rotation Correction and Beyond (17 citations)
- Weakly Supervised AUC Optimization: A Unified Partial AUC Approach (11 citations)
- Instance Consistency Regularization for Semi-Supervised 3D Instance Segmentation (7 citations)
- Randomness Regularization With Simple Consistency Training for Neural Networks (7 citations)
- Triplet Adaptation Framework for Robust Semi-Supervised Learning
OOD and anomaly detection · 7 papers
- RankFeat&RankWeight: Rank-1 Feature/Weight Removal for Out-of-Distribution Detection (30 citations)
- OoD-Control: Generalizing Control in Unseen Environments (29 citations)
- Exploiting Structural Consistency of Chest Anatomy for Unsupervised Anomaly Detection in Radiography Images (22 citations)
- MOODv2: Masked Image Modeling for Out-of-Distribution Detection (19 citations)
- Self-Supervised Anomaly Detection With Neural Transformations (17 citations)
- Low-Dimensional Gradient Helps Out-of-Distribution Detection (13 citations)
- OOD-CV-v2 : An Extended Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images (13 citations)
Knowledge distillation · 5 papers
- Learning From Human Educational Wisdom: A Student-Centered Knowledge Distillation Method (113 citations)
- Pixel Distillation: Cost-Flexible Distillation Across Image Sizes and Heterogeneous Networks (30 citations)
- Unpacking the Gap Box Against Data-Free Knowledge Distillation (25 citations)
- Multimodal Cross-Lingual Summarization for Videos: A Revisit in Knowledge Distillation Induced Triple-Stage Training Method (10 citations)
- On the Distillation of Stories for Transferring Narrative Arcs in Collections of Independent Media (2 citations)
