TPAMI 2021 papers on Label-efficient and robust learning
89 of the 516 papers published in TPAMI 2021 (17.2%) are on Label-efficient and robust learning, compared with 16.3% at TPAMI 2020. They fall into 9 topics.
See TPAMI 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 · 44 papers
- Deep Learning for Person Re-Identification: A Survey and Outlook (2,439 citations)
- The Emerging Trends of Multi-Label Learning (440 citations)
- Adversarial Reciprocal Points Learning for Open Set Recognition (394 citations)
- Learning Generalisable Omni-Scale Representations for Person Re-Identification (381 citations)
- Hyperbolic Deep Neural Networks: A Survey (255 citations)
- GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set (232 citations)
- Affective Image Content Analysis: Two Decades Review and New Perspectives (212 citations)
- Regularizing Deep Networks with Semantic Data Augmentation (179 citations)
- Progressive Learning of Category-Consistent Multi-Granularity Features for Fine-Grained Visual Classification (141 citations)
- End2End Occluded Face Recognition by Masking Corrupted Features (132 citations)
- A Concise Yet Effective Model for Non-Aligned Incomplete Multi-View and Missing Multi-Label Learning (116 citations)
- Feature Completion for Occluded Person Re-Identification (111 citations)
and 32 more in the interactive map.
Domain adaptation and generalization · 18 papers
- Widar3.0: Zero-Effort Cross-Domain Gesture Recognition with Wi-Fi (356 citations)
- Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer (266 citations)
- Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning (157 citations)
- Where and How to Transfer: Knowledge Aggregation-Induced Transferability Perception for Unsupervised Domain Adaptation (149 citations)
- Category-Level Adversarial Adaptation for Semantic Segmentation using Purified Features (126 citations)
- Divergence-Agnostic Unsupervised Domain Adaptation by Adversarial Attacks (123 citations)
- Factors of Influence for Transfer Learning Across Diverse Appearance Domains and Task Types (97 citations)
- Generalized Domain Conditioned Adaptation Network (71 citations)
- A One-Stage Domain Adaptation Network With Image Alignment for Unsupervised Nighttime Semantic Segmentation (64 citations)
- Confidence Estimation via Auxiliary Models (62 citations)
- VideoDG: Generalizing Temporal Relations in Videos to Novel Domains (39 citations)
- Domain-Specific Priors and Meta Learning for Few-Shot First-Person Action Recognition (37 citations)
and 6 more in the interactive map.
Knowledge distillation · 7 papers
- Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks (974 citations)
- Self-Distillation: Towards Efficient and Compact Neural Networks (259 citations)
- Distilled Siamese Networks for Visual Tracking (165 citations)
- Meta-Teacher For Face Anti-Spoofing (92 citations)
- Lifelong Teacher-Student Network Learning (63 citations)
- Distilling Knowledge by Mimicking Features (54 citations)
- Mining Data Impressions from Deep Models as Substitute for the Unavailable Training Data (13 citations)
Self-supervised and contrastive · 6 papers
- ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning (2,601 citations)
- AutoNovel: Automatically Discovering and Learning Novel Visual Categories (268 citations)
- A Self-Supervised Gait Encoding Approach With Locality-Awareness for 3D Skeleton Based Person Re-Identification (105 citations)
- Self-Supervised Learning Across Domains (80 citations)
- Learning by Distillation: A Self-Supervised Learning Framework for Optical Flow Estimation (10 citations)
- Towards Pointsets Representation Learning via Self-Supervised Learning and Set Augmentation
Zero-/few-shot and meta-learning · 5 papers
- Meta-Learning in Neural Networks: A Survey (2,334 citations)
- Bridging the Gap Between Few-Shot and Many-Shot Learning via Distribution Calibration (63 citations)
- How to Trust Unlabeled Data? Instance Credibility Inference for Few-Shot Learning (55 citations)
- Generalized Few-Shot Video Classification With Video Retrieval and Feature Generation (26 citations)
- Learning to Forget for Meta-Learning via Task-and-Layer-Wise Attenuation (19 citations)
Semi-supervised learning · 4 papers
- AbdomenCT-1K: Is Abdominal Organ Segmentation a Solved Problem? (483 citations)
- Improving Semantic Segmentation via Efficient Self-Training (154 citations)
- Triple Generative Adversarial Networks (64 citations)
- A Unified Framework for Automatic Distributed Active Learning (22 citations)
OOD and anomaly detection · 2 papers
Test-time adaptation · 2 papers
- Continual Adaptation for Deep Stereo (36 citations)
- Test-Time Adaptation for Video Frame Interpolation via Meta-Learning (17 citations)
