NeurIPS 2017 accepted papers on Label-efficient and robust learning
46 of the 688 papers accepted at NeurIPS 2017 (6.7%) are on Label-efficient and robust learning, compared with 6.3% at NeurIPS 2016. They fall into 8 topics.
See NeurIPS 2017 in the interactive map
Submitting to NeurIPS? 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 · 23 papers
- Style Transfer from Non-Parallel Text by Cross-Alignment (645 citations)
- Learning Multiple Tasks with Multilinear Relationship Networks (186 citations)
- Learning to Compose Domain-Specific Transformations for Data Augmentation (186 citations)
- Poincaré Embeddings for Learning Hierarchical Representations (170 citations)
- Deep Supervised Discrete Hashing (162 citations)
- Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model (134 citations)
- Maximizing Subset Accuracy with Recurrent Neural Networks in Multi-label Classification (133 citations)
- Learning from Complementary Labels (95 citations)
- Label Distribution Learning Forests (80 citations)
- Spherical convolutions and their application in molecular modelling (72 citations)
- Controllable Invariance through Adversarial Feature Learning (60 citations)
- Inferring Generative Model Structure with Static Analysis (45 citations)
and 11 more in the interactive map.
Semi-supervised learning · 8 papers
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results (1,557 citations)
- Good Semi-supervised Learning That Requires a Bad GAN (229 citations)
- Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference (109 citations)
- Semi-Supervised Learning for Optical Flow with Generative Adversarial Networks (81 citations)
- ExtremeWeather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events (50 citations)
- PixelGAN Autoencoders (25 citations)
- Max-Margin Invariant Features from Transformed Unlabelled Data (4 citations)
- ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching
Zero-/few-shot and meta-learning · 5 papers
- Prototypical Networks for Few-shot Learning (5,178 citations)
- One-Shot Imitation Learning (267 citations)
- Learning to Model the Tail (259 citations)
- Few-Shot Learning Through an Information Retrieval Lens (65 citations)
- Neural Program Meta-Induction
Domain adaptation and generalization · 4 papers
Noisy labels · 2 papers
Test-time adaptation · 2 papers
Knowledge distillation · 1 paper
Self-supervised and contrastive · 1 paper
- Self-Supervised Intrinsic Image Decomposition (94 citations)
