ECCV 2026 accepted papers on Label-efficient and robust learning
184 of the 2,834 papers accepted at ECCV 2026 (6.5%) are on Label-efficient and robust learning, compared with 10.3% at ECCV 2024. They fall into 9 topics.
See ECCV 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 · 51 papers
- SparseDriveV2: Scoring is All You Need for End-to-End Autonomous Driving (38 citations)
- Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives (7 citations)
- This Looks Distinctly Like That: Grounding Interpretable Recognition in Stiefel Geometry against Neural Collapse (5 citations)
- MOJITO: Modal Joint Learning for Unified End-to-End Autonomous Driving (4 citations)
- Driving like yourself: A Benchmark for Closed-Loop Personalized End-to-End Autonomous Driving (3 citations)
- Quantile‑Adaptive Temperature Scaling for Confidence Calibration (2 citations)
- UniTeD: Unified Temporal Diffusion for Joint Perception and Planning in Autonomous Driving (2 citations)
- ASSCG: Just-Right Gating over Chattering for Fast–Slow LLM Planning in Autonomous Driving (1 citation)
- CMCC-ReID: Cross-Modality Clothing-Change Person Re-Identification (1 citation)
- FedLAS: Feature-Modulated Bidirectional Label Smoothing for Neural Network Calibration (1 citation)
- HSFM: Hard-Set-Guided Feature-Space Meta-Learning for Robust Classification under Spurious Correlations (1 citation)
- IMMoE: Incomplete Multi-View Anomaly Detection via Mixture of View Experts Fusion (1 citation)
and 39 more in the interactive map.
Domain adaptation and generalization · 27 papers
- Purify then Guide: Rethinking Domain Generalization for Multimodal Face Anti-Spoofing (6 citations)
- VisCoP: Visual Probing for Video Domain Adaptation of Vision Language Models (2 citations)
- BrainRiem: Riemannian Prototype Learning for Source-Free Cross-Site Brain Network Diagnosis (1 citation)
- Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts (1 citation)
- Rapidly Deploying On-Device Eye Tracking by Distilling Visual Foundation Models (1 citation)
- Semantic-Anchored Evidential Fusion for Domain-Robust Whole-Slide Survival Analysis (1 citation)
- Training-free Cross-domain Few-shot Segmentation via Robust Semantic Representation and Matching (1 citation)
- ASTAD: Asymmetric Style Transfer for Synthetic-to-Real Adaptation in Autonomous Driving
- Bridging Theory and Practice in Source-Free Domain Adaptation via Adversarial Proxy Perturbation
- Context-Aware Joint Alignment for Cross-Scene Hyperspectral Image Classification
- DA-MergeLoRA: Hypernetwork-Based LoRA Merging for Few-Shot Test-Time Domain Adaptation
- Domain Adaptation with Adaptive Imagination for Visual Reinforcement Learning under Limited Target Data
and 15 more in the interactive map.
OOD and anomaly detection · 22 papers
- ArcAD: Anomaly-Rectified Calibration for Cold-Start Supervised Anomaly Detection (1 citation)
- CL-Anomaly: Layer-Adaptive Mixture-of-Experts with Multimodal Large Language Model for Continual Learning in Anomaly Detection (1 citation)
- GroundingAnomaly: Spatially-Grounded Diffusion for Few-Shot Anomaly Synthesis (1 citation)
- MATCH: Flow Matching for Multi-View Anomaly Detection (1 citation)
- BAAF: Universal Transformation of One-Class Classifiers for Unsupervised Image Anomaly Detection
- CMDS-AD: Cross-Modal Dual-Stream Decoupling for Few-Shot Anomaly Detection
- DeCoFlow: Structural Decomposition of Normalizing Flows for Continual Anomaly Detection
- Distribution-Aware Feature Selection for Post-hoc Out-of-Distribution Detection
- Exploiting Local Flatness for Efficient Out-of-Distribution Detection
- Fast Dynamic Prototypes for Unsupervised Anomaly Detection and Localization
- Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detection
- HLRAD: High-dimensional Latent Representation for Unified Anomaly Detection
and 10 more in the interactive map.
Knowledge distillation · 20 papers
- QualiTeacher: Quality-Conditioned Pseudo-Labeling for Real-World Image Restoration (9 citations)
- Pathryoshka: Compressing Pathology Foundation Models via Multi-Teacher Knowledge Distillation with Nested Embeddings (6 citations)
- Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers (2 citations)
- Improving Knowledge Distillation Under Unknown Covariate Shift Through Confidence-Guided Data Augmentation (2 citations)
- Structural Assessment for Understanding and Guiding Dataset Distillation in Discrete Token Space (1 citation)
- Token-level Response-visual Attention Guidance for Multimodal LLMs Knowledge Distillation (1 citation)
- Aggregating Cross-Domain Knowledge via Learnable Tokens for Multi-Teacher Distillation
- Denoising-Enhanced Coarse-to-Fine Infrared Small Target Detection with Attention Prior-Guided Knowledge Distillation
- Distill on a Diet: Efficient Knowledge Distillation via Learnable Data Pruning
- Flash-DD: An Ultra Parameter-Efficient Approach to Dataset Distillation
- From Predictions to Embeddings: Dual Knowledge Distillation for Instance-Dependent Partial Label Learning
- Geometric Foundation Model Distillation for Efficient Lunar 3D Reconstruction
and 8 more in the interactive map.
Self-supervised and contrastive · 18 papers
- MOOZY: A Patient-First Foundation Model for Computational Pathology (4 citations)
- Silhouette-based Gait Foundation Model (4 citations)
- DSeq-JEPA: Discriminative Sequential Joint-Embedding Predictive Architecture (3 citations)
- Human-like Object Grouping in Self-supervised Vision Transformers (3 citations)
- A Mechanism-Driven Theory of Phase Transitions in Active Learning (1 citation)
- BrainFIBRE: A Foundation Model via Information Decomposition for Brain Microstructure (1 citation)
- Pseudo-Stereo Inputs: A Solution to the Occlusion Challenge in Self-Supervised Stereo Matching (1 citation)
- Beyond Isolated Scans: Cross-Phase Alignment of Structure and Topology for 3D Medical Pretraining
- Enlightening Photographic Style Transfer with a Self-Supervised Photographic Embedding
- From Phase to Phenomenon: Self-Supervised Learning of Subsurface Scattering with Minimal Phase-shift Inputs
- Frozen CLIP Priors for Robust Self-Supervised Poisson Inverse Problems
- HASSL: Hierarchy-Aware Self-Supervised Learning Framework for Single Cell Microscopy
and 6 more in the interactive map.
Test-time adaptation · 16 papers
- MMEarth-Bench: Global Model Adaptation via Multimodal Test-Time Training (5 citations)
- Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs (3 citations)
- Learning from Reliable Negatives: Confidence-Anchored Test-Time Adaptation for GUI Grounding (1 citation)
- Multi-Hypothesis Test-Time Adaptation to Mitigate Underspecification (1 citation)
- CS-TTA: Preserving Concept Sensitivity in Test-Time Adaptation
- Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation
- EVEE: Event-Based Online Adaptation for Matching on Unknown Targets
- Memory-Supported Synergistic Adaptation for Training-Free Test-Time Medical Image Segmentation
- MixTTA: Low-Rank Cross-Channel Mixing for Reliable Test-Time Adaptation
- Probe, Anchor, and Amend: Active Test-Time Adaptation of Vision-Language Models
- SPDA: Efficient Online Test-Time Adaptation for Promptable Medical Segmentation
- Stabilizing Real-World Visual Active Tracking with Action-Smooth Test-Time Adaptation
and 4 more in the interactive map.
Zero-/few-shot and meta-learning · 14 papers
- MegaFlow: Zero-Shot Large Displacement Optical Flow (6 citations)
- Lessons and Open Questions from a Unified Study of Camera-Trap Species Recognition Over Time (5 citations)
- WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching (3 citations)
- AquaStereo: Enabling Underwater Stereo Matching via Depth-Conditioned Diffusion and Geometry Self-Distillation (1 citation)
- Keep Your Friends Close, and the Right Neighbours Closer: Disaster-Conditioned Kernel-Regularized Graph Attention for Building Damage Classification (1 citation)
- Match-Any-Events: Zero-Shot Motion-Robust Feature Matching Across Wide Baselines for Event Cameras (1 citation)
- Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition (1 citation)
- Beyond Alignment: A Generative Matching Paradigm via Flow Matching for Zero-Shot Skeleton-Based Action Recognition
- MorphJEPA: Morphology-Aware Latent Prediction for Hyperspectral Images
- SDUM: A Scalable Deep Unrolled Model for Universal Cardiac MRI Reconstruction
- Variational Patch Gating for Training-Free Few-Shot Classification
- Sim, Yet Same: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds
and 2 more in the interactive map.
Semi-supervised learning · 10 papers
- Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective (2 citations)
- Beyond Random Sampling: Distribution-Aware Alignment for Semi-Supervised Medical Image Segmentation (1 citation)
- Geometric Regularization for Long-Tailed Semi-Supervised Learning via Gaussian Feature Bridges (1 citation)
- RePL: Pseudo-label Refinement for Semi-supervised LiDAR Semantic Segmentation (1 citation)
- A Dual-space Patch-driven Complementary Learning Framework for Semi-supervised Multi-organ Segmentation
- Debiased Textual Prompt Tuning for Enhancing Unknown Class Discovery
- Exclusivity-Guided Mask Learning for Semi-Supervised Crowd Instance Segmentation and Counting
- From Local Geometry to Global Pseudo-Labeling for Robust Positive–Unlabeled Learning under Covariate Shift
- Geometric Gradient Rectification for Safe Open-Set Semi-Supervised Learning
- SCDL: Synergistic Confidence-Dispersion Learning for Semi-Supervised Video Polyp Segmentation
Noisy labels · 6 papers
- Why Can Accurate Models Be Learned from Inaccurate Annotations? (1 citation)
- Mask-guided Semantic Alignment: Robust Learning with Noisy Labels via Temporal Attention Stability
- Maximum Spanning Tree Guided Confidence and Sparse Graph for Robust Noisy Label Learning
- Noise-Robust Facial Expression Recognition via Mamba-driven Neighbor Weight Refinement
- Deep Noise Label Learning via Effective Rank Reduction
- Noise-Robust Face Recognition via Non-target Similarity Distribution Guided Sample Selection
