ICCV 2019 accepted papers on Label-efficient and robust learning
161 of the 1,075 papers accepted at ICCV 2019 (15.0%) are on Label-efficient and robust learning, compared with 12.9% at ICCV 2017. They fall into 9 topics.
See ICCV 2019 in the interactive map
Submitting to ICCV? Checklist →
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 · 71 papers
- Omni-Scale Feature Learning for Person Re-Identification (1,197 citations)
- Pose-Guided Feature Alignment for Occluded Person Re-Identification (692 citations)
- ABD-Net: Attentive but Diverse Person Re-Identification (611 citations)
- RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment (603 citations)
- Mixed High-Order Attention Network for Person Re-Identification (437 citations)
- SoftTriple Loss: Deep Metric Learning Without Triplet Sampling (427 citations)
- Learning With Average Precision: Training Image Retrieval With a Listwise Loss (426 citations)
- Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations (385 citations)
- Probabilistic Face Embeddings (368 citations)
- Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition (360 citations)
- Context-Aware Emotion Recognition Networks (336 citations)
- Learning to Discover Novel Visual Categories via Deep Transfer Clustering (323 citations)
and 59 more in the interactive map.
Domain adaptation and generalization · 39 papers
- Moment Matching for Multi-Source Domain Adaptation (1,822 citations)
- Confidence Regularized Self-Training (885 citations)
- Semi-Supervised Domain Adaptation via Minimax Entropy (722 citations)
- Self-Similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-Identification (573 citations)
- Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptation (548 citations)
- Episodic Training for Domain Generalization (445 citations)
- Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization Without Accessing Target Domain Data (400 citations)
- Racial Faces in the Wild: Reducing Racial Bias by Information Maximization Adaptation Network (375 citations)
- Domain Adaptation for Structured Output via Discriminative Patch Representations (335 citations)
- Domain Adaptation for Semantic Segmentation With Maximum Squares Loss (321 citations)
- Self-Training With Progressive Augmentation for Unsupervised Cross-Domain Person Re-Identification (282 citations)
- Self-Ensembling With GAN-Based Data Augmentation for Domain Adaptation in Semantic Segmentation (267 citations)
and 27 more in the interactive map.
Zero-/few-shot and meta-learning · 17 papers
- Few-Shot Image Recognition With Knowledge Transfer (252 citations)
- Transferable Contrastive Network for Generalized Zero-Shot Learning (226 citations)
- Diversity With Cooperation: Ensemble Methods for Few-Shot Classification (214 citations)
- Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning (212 citations)
- Few-Shot Learning With Embedded Class Models and Shot-Free Meta Training (199 citations)
- Attribute Attention for Semantic Disambiguation in Zero-Shot Learning (175 citations)
- Task-Driven Modular Networks for Zero-Shot Compositional Learning (174 citations)
- Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective (147 citations)
- PARN: Position-Aware Relation Networks for Few-Shot Learning (136 citations)
- Semantic-Aware Knowledge Preservation for Zero-Shot Sketch-Based Image Retrieval (131 citations)
- Few-Shot Learning With Global Class Representations (120 citations)
- Modeling Inter and Intra-Class Relations in the Triplet Loss for Zero-Shot Learning (114 citations)
and 5 more in the interactive map.
Semi-supervised learning · 10 papers
- Invariant Information Clustering for Unsupervised Image Classification and Segmentation (815 citations)
- S4L: Self-Supervised Semi-Supervised Learning (780 citations)
- Dual Student: Breaking the Limits of the Teacher in Semi-Supervised Learning (298 citations)
- Prior-Aware Neural Network for Partially-Supervised Multi-Organ Segmentation (204 citations)
- Universal Semi-Supervised Semantic Segmentation (122 citations)
- Aggregation via Separation: Boosting Facial Landmark Detector With Semi-Supervised Style Translation (101 citations)
- Semi-Supervised Learning by Augmented Distribution Alignment (85 citations)
- Laplace Landmark Localization (58 citations)
- MONET: Multiview Semi-Supervised Keypoint Detection via Epipolar Divergence (52 citations)
- Semi-Supervised Skin Detection by Network With Mutual Guidance (28 citations)
Knowledge distillation · 9 papers
- Similarity-Preserving Knowledge Distillation (1,227 citations)
- Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation (1,082 citations)
- Learning Lightweight Lane Detection CNNs by Self Attention Distillation (826 citations)
- A Comprehensive Overhaul of Feature Distillation (740 citations)
- On the Efficacy of Knowledge Distillation (737 citations)
- Correlation Congruence for Knowledge Distillation (629 citations)
- Knowledge Distillation via Route Constrained Optimization (205 citations)
- Distilling Knowledge From a Deep Pose Regressor Network (130 citations)
- Customizing Student Networks From Heterogeneous Teachers via Adaptive Knowledge Amalgamation (60 citations)
Self-supervised and contrastive · 6 papers
- Boosting Few-Shot Visual Learning With Self-Supervision (447 citations)
- Scaling and Benchmarking Self-Supervised Visual Representation Learning (363 citations)
- Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses (280 citations)
- Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localization (74 citations)
- Self-Supervised Representation Learning From Multi-Domain Data (48 citations)
- Self-Supervised Representation Learning via Neighborhood-Relational Encoding (39 citations)
Noisy labels · 5 papers
- Symmetric Cross Entropy for Robust Learning With Noisy Labels (1,088 citations)
- Deep Self-Learning From Noisy Labels (340 citations)
- NLNL: Negative Learning for Noisy Labels (331 citations)
- O2U-Net: A Simple Noisy Label Detection Approach for Deep Neural Networks (267 citations)
- Co-Mining: Deep Face Recognition With Noisy Labels (121 citations)
OOD and anomaly detection · 3 papers
- Memorizing Normality to Detect Anomaly: Memory-Augmented Deep Autoencoder for Unsupervised Anomaly Detection (2,024 citations)
- GODS: Generalized One-Class Discriminative Subspaces for Anomaly Detection (181 citations)
- Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancy (148 citations)
