IJCV 2025 papers on Label-efficient and robust learning
44 of the 266 papers published in IJCV 2025 (16.5%) are on Label-efficient and robust learning, compared with 25.1% at IJCV 2024. They fall into 9 topics.
See IJCV 2025 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 · 13 papers
- DeepFake-Adapter: Dual-Level Adapter for DeepFake Detection (59 citations)
- Sample-Cohesive Pose-Aware Contrastive Facial Representation Learning (32 citations)
- Semantic-Aligned Learning with Collaborative Refinement for Unsupervised VI-ReID (19 citations)
- Unknown Support Prototype Set for Open Set Recognition (13 citations)
- Local Concept Embeddings for Analysis of Concept Distributions in Vision DNN Feature Spaces (7 citations)
- FourierMIL: Fourier Filtering-based Multiple Instance Learning for Whole Slide Image Analysis (6 citations)
- Img2Tab: Automatic Class Relevant Concept Discovery from StyleGAN Features for Explainable Image Classification (6 citations)
- Multi-Prototype Hyperbolic Learning Guided by Class Hierarchy (6 citations)
- A Solution to Co-occurrence Bias in Pedestrian Attribute Recognition: Theory, Algorithms, and Improvements (5 citations)
- Delving Deep into Simplicity Bias for Long-Tailed Image Recognition (5 citations)
- Layered Semi-Second-Order Information Bottleneck and Auxiliary Domain Classification for Person Re-Identification (3 citations)
- Simplified Concrete Dropout - Improving the Generation of Attribution Masks for Fine-grained Classification (2 citations)
and 1 more in the interactive map.
Domain adaptation and generalization · 9 papers
- Multi-Source Domain Adaptation by Causal-Guided Adaptive Multimodal Diffusion Networks (57 citations)
- Analysing Satellite Imagery Classification under Spatial Domain Shift across Geographic Regions (17 citations)
- General Class-Balanced Multicentric Dynamic Prototype Pseudo-Labeling for Source-Free Domain Adaptation (8 citations)
- Unsupervised Robust Domain Adaptation: Paradigm, Theory and Algorithm (8 citations)
- Free Lunch to Meet the Gap: Intermediate Domain Reconstruction for Cross-Domain Few-Shot Learning (6 citations)
- Multi-modal Prompt Alignment with Fine-grained LLM Knowledge for Unsupervised Domain Adaptation (5 citations)
- Boosting Domain Generalization in Remote Sensing Image Segmentation via Style Mapping and General Prototypical Contrast (3 citations)
- Imbuing, Enrichment and Calibration: Leveraging Language for Unseen Domain Extension (1 citation)
- From Small to Large: In-Context Learning as a New Paradigm for Domain Generalization
Self-supervised and contrastive · 9 papers
- Masked Image Modeling: A Survey (66 citations)
- A Closer Look at Benchmarking Self-supervised Pre-training with Image Classification (22 citations)
- Self-Supervised Learning for Text Recognition: A Critical Survey (19 citations)
- Hyperspectral and Multispectral Image Fusion with Arbitrary Resolution Through Self-Supervised Representations (15 citations)
- Bootstrapping Vision-Language Models for Frequency-Centric Self-Supervised Remote Physiological Measurement (8 citations)
- Rethinking Generalizability and Discriminability of Self-Supervised Learning from Evolutionary Game Theory Perspective (8 citations)
- A Causal Intervention Method for Domain Generalization with a Self-Supervised Auxiliary Task (3 citations)
- Investigating Self-Supervised Methods for Label-Efficient Learning (3 citations)
- Self-supervised Shutter Unrolling with Events (3 citations)
Semi-supervised learning · 5 papers
- PICK: Predict and Mask for Semi-supervised Medical Image Segmentation (83 citations)
- Realistic Evaluation of Deep Active Learning for Image Classification and Semantic Segmentation (22 citations)
- UMSCS: A Novel Unpaired Multimodal Image Segmentation Method Via Cross-Modality Generative and Semi-supervised Learning (12 citations)
- An Empirical Study on Training Paradigms for Deep Supervised Hashing (4 citations)
- Dual Consistency Matching for Semi-Supervised Semantic Correspondence
Zero-/few-shot and meta-learning · 3 papers
OOD and anomaly detection · 2 papers
Knowledge distillation · 1 paper
- EdgeSAM: Prompt-In-the-Loop Distillation for SAM (92 citations)
Test-time adaptation · 1 paper
Noisy labels · 1 paper
- RML++: Regroup Median Loss for Combating Label Noise (3 citations)
