IJCV 2021 papers on Label-efficient and robust learning
21 of the 130 papers published in IJCV 2021 (16.2%) are on Label-efficient and robust learning, compared with 12.6% at IJCV 2020. They fall into 6 topics.
See IJCV 2021 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 · 8 papers
- Mitigating Demographic Bias in Facial Datasets with Style-Based Multi-attribute Transfer (67 citations)
- LAMP-HQ: A Large-Scale Multi-pose High-Quality Database and Benchmark for NIR-VIS Face Recognition (48 citations)
- Cascaded Split-and-Aggregate Learning with Feature Recombination for Pedestrian Attribute Recognition (46 citations)
- Intra-Camera Supervised Person Re-Identification (45 citations)
- Joint Bilateral-Resolution Identity Modeling for Cross-Resolution Person Re-Identification (27 citations)
- Letter-Level Online Writer Identification (18 citations)
- Norm-Aware Embedding for Efficient Person Search and Tracking (18 citations)
- Development and Validation of an Unsupervised Feature Learning System for Leukocyte Characterization and Classification: A Multi-Hospital Study (7 citations)
Domain adaptation and generalization · 6 papers
- Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation (562 citations)
- Scale-Aware Domain Adaptive Faster R-CNN (144 citations)
- Hierarchical Domain-Adapted Feature Learning for Video Saliency Prediction (89 citations)
- MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation (82 citations)
- Unsupervised Domain Adaptation with Background Shift Mitigating for Person Re-Identification (45 citations)
- DLOW: Domain Flow and Applications (29 citations)
