IJCV 2023 papers on Label-efficient and robust learning
37 of the 220 papers published in IJCV 2023 (16.8%) are on Label-efficient and robust learning, compared with 14.1% at IJCV 2022. They fall into 7 topics.
See IJCV 2023 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 · 13 papers
- MixStyle Neural Networks for Domain Generalization and Adaptation (209 citations)
- Source-Free Domain Adaptation via Target Prediction Distribution Searching (83 citations)
- Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization (55 citations)
- Universal Representations: A Unified Look at Multiple Task and Domain Learning (42 citations)
- Adversarial Learning Domain-Invariant Conditional Features for Robust Face Anti-spoofing (37 citations)
- Crots: Cross-Domain Teacher–Student Learning for Source-Free Domain Adaptive Semantic Segmentation (30 citations)
- Improving Domain Adaptation Through Class Aware Frequency Transformation (14 citations)
- Intra- & Extra-Source Exemplar-Based Style Synthesis for Improved Domain Generalization (11 citations)
- MineGAN++: Mining Generative Models for Efficient Knowledge Transfer to Limited Data Domains (11 citations)
- Adapting Across Domains via Target-Oriented Transferable Semantic Augmentation Under Prototype Constraint (9 citations)
- Discriminative Noise Robust Sparse Orthogonal Label Regression-Based Domain Adaptation (9 citations)
- Exploiting Inter-Sample Affinity for Knowability-Aware Universal Domain Adaptation (9 citations)
and 1 more in the interactive map.
Recognition and long-tail · 12 papers
- SMG: A Micro-gesture Dataset Towards Spontaneous Body Gestures for Emotional Stress State Analysis (80 citations)
- Efficient Person Search: An Anchor-Free Approach (36 citations)
- Hierarchical Skeleton Meta-Prototype Contrastive Learning with Hard Skeleton Mining for Unsupervised Person Re-identification (29 citations)
- Mimic before Reconstruct: Enhancing Masked Autoencoders with Feature Mimicking (27 citations)
- Attribute-Image Person Re-identification via Modal-Consistent Metric Learning (22 citations)
- Deeply Explain CNN Via Hierarchical Decomposition (16 citations)
- Poincaré Kernels for Hyperbolic Representations (12 citations)
- Semantic Contrastive Bootstrapping for Single-Positive Multi-label Recognition (11 citations)
- SPL-Net: Spatial-Semantic Patch Learning Network for Facial Attribute Recognition with Limited Labeled Data (8 citations)
- A2B: Anchor to Barycentric Coordinate for Robust Correspondence (6 citations)
- GenKL: An Iterative Framework for Resolving Label Ambiguity and Label Non-conformity in Web Images Via a New Generalized KL Divergence (5 citations)
- Learning Dynamic Prototypes for Visual Pattern Debiasing (5 citations)
Self-supervised and contrastive · 4 papers
- Context Autoencoder for Self-supervised Representation Learning (458 citations)
- RELAX: Representation Learning Explainability (17 citations)
- RAFT-MSF: Self-Supervised Monocular Scene Flow Using Recurrent Optimizer (12 citations)
- Self-supervised Secondary Landmark Detection via 3D Representation Learning (11 citations)
Semi-supervised learning · 3 papers
- Semi-Supervised Domain Generalization with Stochastic StyleMatch (77 citations)
- Semi-supervised Visual Tracking of Marine Animals Using Autonomous Underwater Vehicles (62 citations)
- Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation (57 citations)
Zero-/few-shot and meta-learning · 3 papers
Knowledge distillation · 1 paper
OOD and anomaly detection · 1 paper
- Full-Spectrum Out-of-Distribution Detection (72 citations)
