ICML 2016 accepted papers on Label-efficient and robust learning
22 of the 322 papers accepted at ICML 2016 (6.8%) are on Label-efficient and robust learning. They fall into 5 topics.
See ICML 2016 in the interactive map
Submitting to ICML? 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 · 13 papers
- Autoencoding beyond pixels using a learned similarity metric (1,136 citations)
- From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification (454 citations)
- Large-Margin Softmax Loss for Convolutional Neural Networks (431 citations)
- Unsupervised Deep Embedding for Clustering Analysis (115 citations)
- Extreme F-measure Maximization using Sparse Probability Estimates (63 citations)
- Conditional Bernoulli Mixtures for Multi-label Classification (32 citations)
- A Deep Learning Approach to Unsupervised Ensemble Learning (29 citations)
- ADIOS: Architectures Deep In Output Space (25 citations)
- Simultaneous Safe Screening of Features and Samples in Doubly Sparse Modeling (15 citations)
- Structured Prediction Energy Networks (15 citations)
- The Label Complexity of Mixed-Initiative Classifier Training (8 citations)
- Differential Geometric Regularization for Supervised Learning of Classifiers (1 citation)
and 1 more in the interactive map.
Semi-supervised learning · 3 papers
Noisy labels · 3 papers
Domain adaptation and generalization · 2 papers
- Domain Adaptation with Conditional Transferable Components (208 citations)
- A New PAC-Bayesian Perspective on Domain Adaptation (30 citations)
