TPAMI 2022 papers on Label-efficient and robust learning
104 of the 583 papers published in TPAMI 2022 (17.8%) are on Label-efficient and robust learning, compared with 17.2% at TPAMI 2021. They fall into 8 topics.
See TPAMI 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 · 44 papers
- Trusted Multi-View Classification With Dynamic Evidential Fusion (712 citations)
- TransFuser: Imitation With Transformer-Based Sensor Fusion for Autonomous Driving (616 citations)
- Deep Gait Recognition: A Survey (345 citations)
- Deep Learning for Instance Retrieval: A Survey (314 citations)
- Deep Learning for Face Anti-Spoofing: A Survey (286 citations)
- ResLT: Residual Learning for Long-tailed Recognition (161 citations)
- Learning Representation for Clustering Via Prototype Scattering and Positive Sampling (147 citations)
- Class-Specific Semantic Reconstruction for Open Set Recognition (111 citations)
- Disentangled Representation Learning for Recommendation (101 citations)
- Orientational Distribution Learning with Hierarchical Spatial Attention for Open Set Recognition (73 citations)
- CASIA-E: A Large Comprehensive Dataset for Gait Recognition (70 citations)
- When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework and a New Benchmark (70 citations)
and 32 more in the interactive map.
Domain adaptation and generalization · 21 papers
- Domain Generalization: A Survey (1,526 citations)
- Semi-Supervised Heterogeneous Domain Adaptation: Theory and Algorithms (89 citations)
- Cross-Modal Learning for Domain Adaptation in 3D Semantic Segmentation (80 citations)
- Out-of-Domain Generalization From a Single Source: An Uncertainty Quantification Approach (54 citations)
- Maximum Structural Generation Discrepancy for Unsupervised Domain Adaptation (47 citations)
- BuresNet: Conditional Bures Metric for Transferable Representation Learning (43 citations)
- Neuron Coverage-Guided Domain Generalization (41 citations)
- Partial Domain Adaptation Without Domain Alignment (41 citations)
- From Big to Small: Adaptive Learning to Partial-Set Domains (39 citations)
- Learning to Adapt Across Dual Discrepancy for Cross-Domain Person Re-Identification (38 citations)
- Towards Accurate and Robust Domain Adaptation Under Multiple Noisy Environments (38 citations)
- Unsupervised and Semi-Supervised Robust Spherical Space Domain Adaptation (37 citations)
and 9 more in the interactive map.
Zero-/few-shot and meta-learning · 13 papers
- A Review of Generalized Zero-Shot Learning Methods (532 citations)
- DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning (169 citations)
- Learning Graph Embeddings for Open World Compositional Zero-Shot Learning (102 citations)
- TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learning (88 citations)
- Few-Shot Learning With a Strong Teacher (86 citations)
- Towards Zero-Shot Sign Language Recognition (66 citations)
- Reinforcing Generated Images via Meta-Learning for One-Shot Fine-Grained Visual Recognition (62 citations)
- Revisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot Tasks (37 citations)
- PatchMix Augmentation to Identify Causal Features in Few-Shot Learning (30 citations)
- Bayesian Embeddings for Few-Shot Open World Recognition (29 citations)
- Dataset Bias in Few-Shot Image Recognition (28 citations)
- PAC-Bayes Meta-Learning With Implicit Task-Specific Posteriors (13 citations)
and 1 more in the interactive map.
Self-supervised and contrastive · 8 papers
- ResMLP: Feedforward Networks for Image Classification With Data-Efficient Training (952 citations)
- Contrastive Learning with Stronger Augmentations (293 citations)
- Multi-Granularity Anchor-Contrastive Representation Learning for Semi-Supervised Skeleton-Based Action Recognition (170 citations)
- Seed the Views: Hierarchical Semantic Alignment for Contrastive Representation Learning (48 citations)
- Self-Adaptive Training: Bridging Supervised and Self-Supervised Learning (45 citations)
- Towards JPEG-Resistant Image Forgery Detection and Localization Via Self-Supervised Domain Adaptation (28 citations)
- Micro-Supervised Disturbance Learning: A Perspective of Representation Probability Distribution (22 citations)
- E3 Outlier: a Self-Supervised Framework for Unsupervised Deep Outlier Detection (16 citations)
Semi-supervised learning · 7 papers
- Semi-Supervised and Unsupervised Deep Visual Learning: A Survey (266 citations)
- Minimizing Estimated Risks on Unlabeled Data: A New Formulation for Semi-Supervised Medical Image Segmentation (64 citations)
- Hypergraph Collaborative Network on Vertices and Hyperedges (55 citations)
- Improved Generalization in Semi-Supervised Learning: A Survey of Theoretical Results (55 citations)
- MaxMatch: Semi-Supervised Learning With Worst-Case Consistency (36 citations)
- Memory Uncertainty Learning for Real-World Single Image Deraining (35 citations)
- Reducing Spatial Labeling Redundancy for Active Semi-Supervised Crowd Counting (19 citations)
Knowledge distillation · 6 papers
- Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for Classification (40 citations)
- Generalized Knowledge Distillation via Relationship Matching (26 citations)
- Dynamic Self-Supervised Teacher-Student Network Learning (22 citations)
- Learning to Explore Distillability and Sparsability: A Joint Framework for Model Compression (22 citations)
- Stereo Confidence Estimation via Locally Adaptive Fusion and Knowledge Distillation (7 citations)
- Efficient Image and Sentence Matching
