AAAI 2017 accepted papers on Label-efficient and robust learning
100 of the 639 papers accepted at AAAI 2017 (15.6%) are on Label-efficient and robust learning, compared with 19.7% at AAAI 2016. They fall into 8 topics.
See AAAI 2017 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 · 75 papers
- Unsupervised Deep Learning for Optical Flow Estimation (295 citations)
- Label-Free Supervision of Neural Networks with Physics and Domain Knowledge (288 citations)
- Learning Deep Latent Space for Multi-Label Classification (246 citations)
- POI2Vec: Geographical Latent Representation for Predicting Future Visitors (234 citations)
- A Multi-Task Deep Network for Person Re-Identification (206 citations)
- Learning Visual Sentiment Distributions via Augmented Conditional Probability Neural Network (172 citations)
- Deep MIML Network (165 citations)
- Learning Invariant Deep Representation for NIR-VIS Face Recognition (162 citations)
- Attributes for Improved Attributes: A Multi-Task Network Utilizing Implicit and Explicit Relationships for Facial Attribute Classification (152 citations)
- Identifying Unknown Unknowns in the Open World: Representations and Policies for Guided Exploration (148 citations)
- Active Discriminative Text Representation Learning (128 citations)
- Column Networks for Collective Classification (111 citations)
and 63 more in the interactive map.
Domain adaptation and generalization · 9 papers
- Distant Domain Transfer Learning (196 citations)
- Recurrent Neural Networks with Auxiliary Labels for Cross-Domain Opinion Target Extraction (121 citations)
- What Do Multiwinner Voting Rules Do? An Experiment Over the Two-Dimensional Euclidean Domain (62 citations)
- Fast Generalized Distillation for Semi-Supervised Domain Adaptation (54 citations)
- Sparse Deep Transfer Learning for Convolutional Neural Network (45 citations)
- Unsupervised Domain Adaptation with a Relaxed Covariate Shift Assumption (27 citations)
- Cross-Domain Kernel Induction for Transfer Learning (15 citations)
- Fredholm Multiple Kernel Learning for Semi-Supervised Domain Adaptation (14 citations)
- Active Learning with Cross-Class Similarity Transfer (10 citations)
Semi-supervised learning · 9 papers
- Variational Autoencoder for Semi-Supervised Text Classification (199 citations)
- A Unified Model for Cross-Domain and Semi-Supervised Named Entity Recognition in Chinese Social Media (128 citations)
- Learning Safe Prediction for Semi-Supervised Regression (69 citations)
- Semi-Supervised Adaptive Label Distribution Learning for Facial Age Estimation (44 citations)
- Semi-Supervised Multi-View Correlation Feature Learning with Application to Webpage Classification (37 citations)
- Universum Prescription: Regularization Using Unlabeled Data (28 citations)
- Semi-Supervised Classifications via Elastic and Robust Embedding (24 citations)
- Discriminative Semi-Supervised Dictionary Learning with Entropy Regularization for Pattern Classification (19 citations)
- Bootstrapping Distantly Supervised IE Using Joint Learning and Small Well-Structured Corpora (5 citations)
Zero-/few-shot and meta-learning · 2 papers
Knowledge distillation · 2 papers
Self-supervised and contrastive · 1 paper
- Self-Paced Learning: An Implicit Regularization Perspective (51 citations)
Noisy labels · 1 paper
- Robust Loss Functions under Label Noise for Deep Neural Networks (1,012 citations)
Test-time adaptation · 1 paper
- Resource Constrained Structured Prediction (4 citations)
