IJCV 2024 papers on Label-efficient and robust learning
86 of the 343 papers published in IJCV 2024 (25.1%) are on Label-efficient and robust learning, compared with 16.8% at IJCV 2023. They fall into 9 topics.
See IJCV 2024 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 · 25 papers
- A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking (163 citations)
- Hyperbolic Deep Learning in Computer Vision: A Survey (107 citations)
- Open Set Recognition in Real World (41 citations)
- Heterogeneous Semantic Transfer for Multi-label Recognition with Partial Labels (36 citations)
- Species-Agnostic Patterned Animal Re-identification by Aggregating Deep Local Features (35 citations)
- Automated Detection of Cat Facial Landmarks (30 citations)
- Interweaving Insights: High-Order Feature Interaction for Fine-Grained Visual Recognition (30 citations)
- Exploring Homogeneous and Heterogeneous Consistent Label Associations for Unsupervised Visible-Infrared Person ReID (28 citations)
- Uncertainty Modeling for Group Re-Identification (28 citations)
- Exploring the Usage of Pre-trained Features for Stereo Matching (27 citations)
- Deep Learning Based Prediction of Pulmonary Hypertension in Newborns Using Echocardiograms (25 citations)
- Fine-Grained Multimodal DeepFake Classification via Heterogeneous Graphs (25 citations)
and 13 more in the interactive map.
Domain adaptation and generalization · 23 papers
- Learning Hierarchical Visual Transformation for Domain Generalizable Visual Matching and Recognition (41 citations)
- Source-Free Domain Adaptation Guided by Vision and Vision-Language Pre-training (28 citations)
- Domain Generalization via Ensemble Stacking for Face Presentation Attack Detection (27 citations)
- Towards Data-Centric Face Anti-spoofing: Improving Cross-Domain Generalization via Physics-Based Data Synthesis (27 citations)
- Towards Unsupervised Domain Adaptation via Domain-Transformer (25 citations)
- Bridging the Source-to-Target Gap for Cross-Domain Person Re-identification with Intermediate Domains (24 citations)
- Domain Generalization with Small Data (22 citations)
- Kill Two Birds with One Stone: Domain Generalization for Semantic Segmentation via Network Pruning (20 citations)
- CSDG-FAS: Closed-Space Domain Generalization for Face Anti-spoofing (15 citations)
- Learning to Generalize over Subpartitions for Heterogeneity-Aware Domain Adaptive Nuclei Segmentation (14 citations)
- Open-Set Single-Domain Generalization for Robust Face Anti-Spoofing (14 citations)
- Pulling Target to Source: A New Perspective on Domain Adaptive Semantic Segmentation (14 citations)
and 11 more in the interactive map.
OOD and anomaly detection · 9 papers
- Generalized Out-of-Distribution Detection: A Survey (1,463 citations)
- Dissecting Out-of-Distribution Detection and Open-Set Recognition: A Critical Analysis of Methods and Benchmarks (25 citations)
- Augmenting the Softmax with Additional Confidence Scores for Improved Selective Classification with Out-of-Distribution Data (20 citations)
- Winning Prize Comes from Losing Tickets: Improve Invariant Learning by Exploring Variant Parameters for Out-of-Distribution Generalization (18 citations)
- Hard-Normal Example-Aware Template Mutual Matching for Industrial Anomaly Detection (12 citations)
- Rethinking Out-of-Distribution Detection From a Human-Centric Perspective (9 citations)
- Visual Out-of-Distribution Detection in Open-Set Noisy Environments (9 citations)
- Out-of-Distribution Detection with Virtual Outlier Smoothing (8 citations)
- Revisiting Deep Ensemble for Out-of-Distribution Detection: A Loss Landscape Perspective (6 citations)
Knowledge distillation · 8 papers
- Knowledge Distillation Meets Open-Set Semi-supervised Learning (28 citations)
- Cross-Architecture Knowledge Distillation (27 citations)
- Relation-Guided Adversarial Learning for Data-Free Knowledge Transfer (10 citations)
- RNAS-CL: Robust Neural Architecture Search by Cross-Layer Knowledge Distillation (8 citations)
- Descriptor Distillation: A Teacher-Student-Regularized Framework for Learning Local Descriptors (6 citations)
- Multi-teacher Universal Distillation Based on Information Hiding for Defense Against Facial Manipulation (2 citations)
- S$$^{2}$$P$$^{3}$$: Self-Supervised Polarimetric Pose Prediction (1 citation)
- On Mitigating Stability-Plasticity Dilemma in CLIP-guided Image Morphing via Geodesic Distillation Loss
Noisy labels · 6 papers
- Robust Object Re-identification with Coupled Noisy Labels (57 citations)
- SplitNet: Learnable Clean-Noisy Label Splitting for Learning with Noisy Labels (24 citations)
- Variational Rectification Inference for Learning with Noisy Labels (19 citations)
- Instance-dependent Label Distribution Estimation for Learning with Label Noise (18 citations)
- Combating Label Noise with a General Surrogate Model for Sample Selection (8 citations)
- Learning with Noisy Correspondence (6 citations)
Self-supervised and contrastive · 5 papers
- Rethinking Vision Transformer and Masked Autoencoder in Multimodal Face Anti-Spoofing (83 citations)
- View-Invariant Skeleton Action Representation Learning via Motion Retargeting (36 citations)
- Self-supervised Scalable Deep Compressed Sensing (28 citations)
- Slimmable Networks for Contrastive Self-supervised Learning (6 citations)
- On the Generalization and Causal Explanation in Self-Supervised Learning (4 citations)
Semi-supervised learning · 4 papers
- PRCL: Probabilistic Representation Contrastive Learning for Semi-Supervised Semantic Segmentation (36 citations)
- Exploration and Exploitation of Unlabeled Data for Open-Set Semi-supervised Learning (8 citations)
- R$$^{2}$$S100K: Road-Region Segmentation Dataset for Semi-supervised Autonomous Driving in the Wild (7 citations)
- InfoPro: Locally Supervised Deep Learning by Maximizing Information Propagation (5 citations)
