TPAMI 2026 papers on Label-efficient and robust learning
110 of the 880 papers published in TPAMI 2026 (12.5%) are on Label-efficient and robust learning, compared with 11.9% at TPAMI 2025. They fall into 9 topics.
See TPAMI 2026 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 · 35 papers
- Representation Learning for Tabular Data: A Comprehensive Survey (79 citations)
- DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving (25 citations)
- A Survey on Archetypal Analysis (20 citations)
- 50 Years of Automated Face Recognition (18 citations)
- Less Is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection (10 citations)
- Trusted Multi-View Learning Under Noisy Supervision (9 citations)
- Label Hierarchy Transition: Delving Into Class Hierarchies to Enhance Deep Classifiers (8 citations)
- Making Binary Classification From Multiple Unlabeled Datasets Almost Free of Supervision (6 citations)
- Robust Trusted Conflictive Multiview Collaborative Contrastive Learning (6 citations)
- Attribution Explanations for Deep Neural Networks: A Theoretical Perspective (4 citations)
- Computational Investigation of Abstraction in Claude Monet’s Water Lilies Through Brushstroke Analysis (3 citations)
- Disentangling Consistent and Specific Information for Double Incomplete Multi-View Multi-Label Classification (3 citations)
and 23 more in the interactive map.
Domain adaptation and generalization · 26 papers
- CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey (33 citations)
- Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models (32 citations)
- DGPDL: Domain-Guided Prompt Distribution Learning for Generalizable Face Anti-Spoofing (5 citations)
- Mitigating Negative Transfer via Reducing Environmental Disagreement (5 citations)
- Learning Representation and Synergy Invariances: A Provable Framework for Generalized Multimodal Face Anti-Spoofing (3 citations)
- Causal Inference via Style Bias Deconfounding for Domain Generalization (2 citations)
- Suppressing Gradient Conflict for Generalizable Deepfake Detection (2 citations)
- Causality-Preserving Domain Generalization via Adaptive Fourier Mixup for RUL Prediction (1 citation)
- Cross-Domain Multi-Person Human Activity Recognition via Near-Field Wi-Fi Sensing (1 citation)
- Feature-Space Planes Searcher: A Universal Domain Adaptation Framework for Interpretability and Computational Efficiency (1 citation)
- Local and High-Order Consistency Coding and Adaptation for Cross-Hypergraph Node Classification (1 citation)
- Active Domain Adaptation Under Concept Shift
and 14 more in the interactive map.
OOD and anomaly detection · 13 papers
- Anomaly Detection and Generation with Diffusion Models: A Survey (20 citations)
- Catching Every Ripple: Enhanced Anomaly Awareness via Dynamic Concept Adaptation (3 citations)
- Kernel PCA for Out-of-Distribution Detection: Non-Linear Kernel Selection and Approximation (3 citations)
- Revisiting Out-of-Distribution Detection in Real-Time Object Detection: From Benchmark Pitfalls to a New Mitigation Paradigm (3 citations)
- CFSM: A Novel Causal Feature Selection Module for Two-Dimensional Out-of-Distribution Generalization (2 citations)
- Outlier-Aware Contrastive Learning (2 citations)
- Quantum Conflict Measurement in Decision Fusion for Out-of-Distribution Detection (2 citations)
- Modeling Spectral-Spatial Attributes for Hyperspectral Anomaly Detection (1 citation)
- On the Two Facets to Conquer Wild Out-of-Distribution Detection (1 citation)
- Reliable Uncertainty Estimation via Discriminative Feature Learning for Evidential Deep Classification (1 citation)
- Feature-Alteration Robustness for Out-of-Distribution Detection
- Instance-Level Cost-Sensitive Hypergraph Learning With Quality-Aware Structure Judgement for Anomaly Detection
and 1 more in the interactive map.
Knowledge distillation · 11 papers
- Generalized Kullback–Leibler Divergence Loss (25 citations)
- Distilling Object Detectors via Monte Carlo Dropout (9 citations)
- Flexible Multi-Level Optimal Transport for Universal Cross-Tokenizer Knowledge Distillation on LLMs and Beyond (2 citations)
- Looking Broader for Knowledge Distillation via Receptive-Field Alignment (2 citations)
- Anticipating Object Interactions Via Aggregation and Distillation of Spatio-Temporal Knowledge From Vision Language Models
- FreeKD+: A Frequency Knowledge Distillation Framework for Dense Prediction
- Selecting and Distilling Cross-Label Models
- Soft Label Pruning and Quantization for Large-Scale Dataset Distillation
- Towards Medical Image Dataset Distillation: A Progressive Trajectory Matching and Dynamic Diversity Enhancing Method
- MAGIC: Meta-Ability Guided Interactive Chain-of-Distillation for Effective-and-Efficient Vision-and-Language Navigation
- Understanding the Effects of Projectors in Knowledge Distillation
Zero-/few-shot and meta-learning · 9 papers
- From Channel Bias to Feature Redundancy: Uncovering the “Less is More” Principle in Few-Shot Learning (17 citations)
- Boosting Learning Efficiency in Few-Shot Tasks With Layer-Adaptive PID Control (12 citations)
- DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-Learning (7 citations)
- Language-4D Cross-Boosting for Generalized Zero-Shot 6DoF Tracking and 3D Reconstruction (1 citation)
- Instruction-Guided Distribution Maximization for General Few-Shot Intent Recognition
- M3R++: Masked Token Mixup and Dual Cross-Modal Masking for Zero-Shot Learning
- Prototype Matters: Domain-Wise Prototype Induction for Zero-Shot Recognition
- Tail Task Risk Minimization in Meta-Learning From Theoretical Advances to Practical Strategies
- ZeroDiff++: Generative Test-Time Adaptation for Zero-shot Learning
Noisy labels · 6 papers
- Dual Geometry Margin Optimization for Coupled-Noisy Robust Ensemble Learning (4 citations)
- Bridging Generative and Discriminative Noisy-Label Learning via Direction-Agnostic EM Formulation (3 citations)
- Learning From Crowds With Multiple Feature Dynamic Fusion-Based Annotation Generation (1 citation)
- Label Distribution Enhancement-Based Label Completion for High-Noise-Ratio Crowdsourcing
- Multi-Round Meta-Learning for Label Purification Without Trusted Labels
- Text-to-Image Diffusion Sample Selector for Learning With Noisy Labels
Semi-supervised learning · 5 papers
- Scalable Semi-Supervised Learning With Discriminative Label Propagation and Correction (12 citations)
- Brightness-Aware Synthetic-to-Real Learning for Nighttime Hazy Image Enhancement (3 citations)
- Decouple Then Converge: Handling Unknown Unlabeled Distributions in Long-Tailed Semi-Supervised Learning (2 citations)
- Semi-Supervised VQA Multi-Modal Explanation via Self-Critical Learning (2 citations)
- Exploring the Stochastic Regularisation in Normalisation Layers for Semi-Supervised Learning (1 citation)
Test-time adaptation · 4 papers
- Adapt in the Wild: Test-Time Entropy Minimization with Sharpness and Feature Regularization (4 citations)
- Dual Uncertainty-Aware Guidance for Test-Time Visual Retrieval Under Distributional Variations
- KaleidoEye: A Large-scale Dataset and Benchmark for Slippage Robust Gaze Tracking in HMDs
- Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation
