AAAI 2019 accepted papers on Label-efficient and robust learning
214 of the 1,147 papers accepted at AAAI 2019 (18.7%) are on Label-efficient and robust learning, compared with 18.4% at AAAI 2018. They fall into 8 topics.
See AAAI 2019 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 · 146 papers
- CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison (3,050 citations)
- Deep Interest Evolution Network for Click-Through Rate Prediction (1,209 citations)
- GaitSet: Regarding Gait as a Set for Cross-View Gait Recognition (710 citations)
- A Bottom-Up Clustering Approach to Unsupervised Person Re-Identification (594 citations)
- Horizontal Pyramid Matching for Person Re-Identification (498 citations)
- Precision-Recall versus Accuracy and the Role of Large Data Sets (377 citations)
- HSME: Hypersphere Manifold Embedding for Visible Thermal Person Re-Identification (298 citations)
- RepeatNet: A Repeat Aware Neural Recommendation Machine for Session-Based Recommendation (289 citations)
- MixUp as Locally Linear Out-of-Manifold Regularization (272 citations)
- Understanding Dropouts in MOOCs (263 citations)
- DAN: Deep Attention Neural Network for News Recommendation (201 citations)
- DeepCF: A Unified Framework of Representation Learning and Matching Function Learning in Recommender System (200 citations)
and 134 more in the interactive map.
Domain adaptation and generalization · 25 papers
- Aligning Domain-Specific Distribution and Classifier for Cross-Domain Classification from Multiple Sources (422 citations)
- Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentation (367 citations)
- Transferable Attention for Domain Adaptation (305 citations)
- Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation (247 citations)
- Depthwise Convolution Is All You Need for Learning Multiple Visual Domains (225 citations)
- Deeply Fusing Reviews and Contents for Cold Start Users in Cross-Domain Recommendation Systems (181 citations)
- Interactive Attention Transfer Network for Cross-Domain Sentiment Classification (122 citations)
- Transferable Curriculum for Weakly-Supervised Domain Adaptation (111 citations)
- Consensus Adversarial Domain Adaptation (77 citations)
- Self-Ensembling Attention Networks: Addressing Domain Shift for Semantic Segmentation (72 citations)
- MotionTransformer: Transferring Neural Inertial Tracking between Domains (64 citations)
- Disjoint Label Space Transfer Learning with Common Factorised Space (59 citations)
and 13 more in the interactive map.
Semi-supervised learning · 14 papers
- A Two-Stream Mutual Attention Network for Semi-Supervised Biomedical Segmentation with Noisy Labels (86 citations)
- Distributionally Robust Semi-Supervised Learning for People-Centric Sensing (48 citations)
- Joint Semi-Supervised Feature Selection and Classification through Bayesian Approach (43 citations)
- Towards Automated Semi-Supervised Learning (24 citations)
- Dual Semi-Supervised Learning for Facial Action Unit Recognition (23 citations)
- LabelForest: Non-Parametric Semi-Supervised Learning for Activity Recognition (18 citations)
- Exploiting Synthetically Generated Data with Semi-Supervised Learning for Small and Imbalanced Datasets (16 citations)
- Distribution-Based Semi-Supervised Learning for Activity Recognition (14 citations)
- Mixture of Expert/Imitator Networks: Scalable Semi-Supervised Learning Framework (8 citations)
- Wasserstein Soft Label Propagation on Hypergraphs: Algorithm and Generalization Error Bounds (5 citations)
- Distantly Supervised Entity Relation Extraction with Adapted Manual Annotations
- Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function
and 2 more in the interactive map.
Zero-/few-shot and meta-learning · 11 papers
- Distribution Consistency Based Covariance Metric Networks for Few-Shot Learning (276 citations)
- From Zero-Shot Learning to Cold-Start Recommendation (158 citations)
- Image Block Augmentation for One-Shot Learning (112 citations)
- A Dual Attention Network with Semantic Embedding for Few-Shot Learning (64 citations)
- Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference (46 citations)
- Learning to Compose Topic-Aware Mixture of Experts for Zero-Shot Video Captioning (36 citations)
- Energy Confused Adversarial Metric Learning for Zero-Shot Image Retrieval and Clustering (29 citations)
- Dual-View Ranking with Hardness Assessment for Zero-Shot Learning (12 citations)
- Hybrid Attention-Based Prototypical Networks for Noisy Few-Shot Relation Classification
- Zero-Shot Adaptive Transfer for Conversational Language Understanding
- Zero-Shot Neural Transfer for Cross-Lingual Entity Linking
Knowledge distillation · 10 papers
- Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons (565 citations)
- Training Deep Neural Networks in Generations: A More Tolerant Teacher Educates Better Students (212 citations)
- Knowledge Tracing Machines: Factorization Machines for Knowledge Tracing (201 citations)
- Data-Distortion Guided Self-Distillation for Deep Neural Networks (189 citations)
- Knowledge Distillation with Adversarial Samples Supporting Decision Boundary (149 citations)
- MEAL: Multi-Model Ensemble via Adversarial Learning (139 citations)
- Amalgamating Knowledge towards Comprehensive Classification (97 citations)
- Iterative Classroom Teaching (13 citations)
- Network Recasting: A Universal Method for Network Architecture Transformation (1 citation)
- Exploiting the Ground-Truth: An Adversarial Imitation Based Knowledge Distillation Approach for Event Detection
Noisy labels · 4 papers
- Crash to Not Crash: Learn to Identify Dangerous Vehicles Using a Simulator (59 citations)
- Safeguarded Dynamic Label Regression for Noisy Supervision (53 citations)
- Soft Facial Landmark Detection by Label Distribution Learning (52 citations)
- Improving Distantly Supervised Relation Extraction with Neural Noise Converter and Conditional Optimal Selector
