IJCV 2026 papers on Label-efficient and robust learning
55 of the 477 papers published in IJCV 2026 (11.5%) are on Label-efficient and robust learning, compared with 16.5% at IJCV 2025. They fall into 9 topics.
See IJCV 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
Domain adaptation and generalization · 24 papers
- Align the GAP: Prior-Based Unified Multi-task Remote Physiological Measurement Framework For Domain Generalization and Personalization (5 citations)
- Let Synthetic Data Shine: Domain Reassembly and Soft-Fusion for Single Domain Generalization (4 citations)
- Wild Animal Tracking with High-Quality Segment Anything Model and Domain Adaptation (4 citations)
- Learning Unknown Spoof Prompts for Generalized Face Anti-Spoofing Using Only Real Face Images (3 citations)
- B$$^{3}$$CT: Three-Branch Learning with Unlabeled Target Signals for Domain-Robust Semantic Segmentation (2 citations)
- Delving into Pre-training for Domain Transfer: A Broad Study of Pre-training for Domain Generalization and Domain Adaptation (2 citations)
- Uncertainty-guided Open-Set Source-Free Unsupervised Domain Adaptation with Target-private Class Segregation (2 citations)
- WildIng: A Wildlife Image Invariant Representation Model for Geographical Domain Shift (2 citations)
- Associative Recurrent Bilinear Optimization for Domain-Generalized Binary Neural Networks (1 citation)
- Domain Adaptation with a Single Vision-Language Embedding (1 citation)
- Source-Free Domain Adaptation with Vision-Language Prior (1 citation)
- DOME: A Decoupled Offline-Online Memory Externalization Framework for Interpretable Domain-Generalized Face Anti-spoofing
and 12 more in the interactive map.
Recognition and long-tail · 12 papers
- MammoDG: Generalisable Deep Learning Advances Cross-Domain Multi-Center Breast Cancer Screening (18 citations)
- SoftHGNN: Soft Hypergraph Neural Networks for General Visual Recognition (11 citations)
- On Combining Animal Re-Identification Models to Address Small Datasets (6 citations)
- Learning Robust Event-Guided Representations for Person Re-Identification (4 citations)
- Generalized Fine-Grained Category Discovery with Multi-Granularity Conceptual Experts (3 citations)
- An Accelerated CNN System for Polyp Classification Targeting Wireless Endoscopy Images
- Dual-Edged Homogeneous-Modality Similarity: Towards Visible-Infrared Modality-Incomplete Person Re-Identification with Modality Adaptive Matching
- Event-Based Facial Expression Recognition via Knowledge-Enhanced Hypergraph Computation
- ManiDream: Manifold Completion via Prototype-Anchored Dreaming for Long-Tailed Visual Recognition
- RareSpot+: A Benchmark, Model, and Active Learning Framework for Small and Rare Wildlife in Aerial Imagery
- Semantic Invariant Representation Learning and Data-Driven Label Prototype Modeling for Incomplete Multi-view Multi-label Classification
- Semantic-Guided Fine-Tuning of Foundation Model for Long-Tailed Visual Recognition
OOD and anomaly detection · 5 papers
- Near OOD Detection for Vision-Language Prompt Learning with Contrastive Logit Score (3 citations)
- Balanced Hyperbolic Embeddings Are Natural Out-of-Distribution Detectors (2 citations)
- ResAD++: Towards Class Agnostic Anomaly Detection via Residual Feature Learning (2 citations)
- GradAlign: Detecting Out-of-Distribution Samples via Gradient Concentration
- Unveiling Representation Expansion: A New Lens on Out-of-Distribution Detection
