IJCV 2022 papers on Label-efficient and robust learning
26 of the 185 papers published in IJCV 2022 (14.1%) are on Label-efficient and robust learning, compared with 16.2% at IJCV 2021. They fall into 6 topics.
See IJCV 2022 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 · 14 papers
- A Survey on Long-Tailed Visual Recognition (182 citations)
- Twin Contrastive Learning for Online Clustering (164 citations)
- Pre-Training Without Natural Images (74 citations)
- Delving into Inter-Image Invariance for Unsupervised Visual Representations (62 citations)
- Adaptive Deep Disturbance-Disentangled Learning for Facial Expression Recognition (48 citations)
- Class-Difficulty Based Methods for Long-Tailed Visual Recognition (47 citations)
- A Deep Learning Approach to Clustering Visual Arts (36 citations)
- Population-Based Evolutionary Gaming for Unsupervised Person Re-identification (22 citations)
- Learning Degradation-Invariant Representation for Robust Real-World Person Re-Identification (18 citations)
- Personalized Convolution for Face Recognition (10 citations)
- Interpreting Face Inference Models Using Hierarchical Network Dissection (6 citations)
- Pairwise Alignment of Archaeological Fragments Through Morphological Characterization of Fracture Surfaces (6 citations)
and 2 more in the interactive map.
Domain adaptation and generalization · 5 papers
- DESC: Domain Adaptation for Depth Estimation via Semantic Consistency (50 citations)
- Project to Adapt: Domain Adaptation for Depth Completion from Noisy and Sparse Sensor Data (31 citations)
- Cross-Domain Gated Learning for Domain Generalization (28 citations)
- Domain-Specific Bias Filtering for Single Labeled Domain Generalization (26 citations)
- AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach (16 citations)
