CVPR 2017 accepted papers on Label-efficient and robust learning
87 of the 783 papers accepted at CVPR 2017 (11.1%) are on Label-efficient and robust learning, compared with 12.8% at CVPR 2016. They fall into 7 topics.
See CVPR 2017 in the interactive map
Submitting to CVPR? 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 · 57 papers
- ChestX-ray8: Hospital-Scale Chest X-Ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases (3,529 citations)
- SphereFace: Deep Hypersphere Embedding for Face Recognition (3,010 citations)
- Re-Ranking Person Re-Identification With k-Reciprocal Encoding (1,534 citations)
- Network Dissection: Quantifying Interpretability of Deep Visual Representations (1,404 citations)
- Reliable Crowdsourcing and Deep Locality-Preserving Learning for Expression Recognition in the Wild (1,404 citations)
- Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-Identification (1,196 citations)
- Learning Deep Context-Aware Features Over Body and Latent Parts for Person Re-Identification (704 citations)
- Context-Aware Correlation Filter Tracking (666 citations)
- Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction (653 citations)
- L2-Net: Deep Learning of Discriminative Patch Descriptor in Euclidean Space (622 citations)
- Detecting Masked Faces in the Wild With LLE-CNNs (464 citations)
- Learning Spatial Regularization With Image-Level Supervisions for Multi-Label Image Classification (383 citations)
and 45 more in the interactive map.
Zero-/few-shot and meta-learning · 12 papers
- Semantic Autoencoder for Zero-Shot Learning (878 citations)
- Zero-Shot Learning - the Good, the Bad and the Ugly (841 citations)
- Zero-Shot Action Recognition With Error-Correcting Output Codes (161 citations)
- Zero-Shot Recognition Using Dual Visual-Semantic Mapping Paths (151 citations)
- From Zero-Shot Learning to Conventional Supervised Classification: Unseen Visual Data Synthesis (150 citations)
- Semantically Consistent Regularization for Zero-Shot Recognition (145 citations)
- Matrix Tri-Factorization With Manifold Regularizations for Zero-Shot Learning (136 citations)
- Low-Rank Embedded Ensemble Semantic Dictionary for Zero-Shot Learning (135 citations)
- Zero-Shot Classification With Discriminative Semantic Representation Learning (129 citations)
- Gaze Embeddings for Zero-Shot Image Classification (109 citations)
- Multi-Attention Network for One Shot Learning (93 citations)
- Automatic Discovery, Association Estimation and Learning of Semantic Attributes for a Thousand Categories (27 citations)
Domain adaptation and generalization · 10 papers
- Adversarial Discriminative Domain Adaptation (5,087 citations)
- Deep Hashing Network for Unsupervised Domain Adaptation (2,078 citations)
- Unsupervised Pixel-Level Domain Adaptation With Generative Adversarial Networks (1,634 citations)
- Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation (619 citations)
- Joint Geometrical and Statistical Alignment for Visual Domain Adaptation (593 citations)
- Domain Adaptation by Mixture of Alignments of Second- or Higher-Order Scatter Tensors (125 citations)
- Learning an Invariant Hilbert Space for Domain Adaptation (119 citations)
- A Compact DNN: Approaching GoogLeNet-Level Accuracy of Classification and Domain Adaptation (56 citations)
- Correlational Gaussian Processes for Cross-Domain Visual Recognition (38 citations)
- Unsupervised Adaptive Re-Identification in Open World Dynamic Camera Networks (33 citations)
Noisy labels · 3 papers
- Making Deep Neural Networks Robust to Label Noise: A Loss Correction Approach (1,463 citations)
- Learning From Noisy Large-Scale Datasets With Minimal Supervision (481 citations)
- Attend in Groups: A Weakly-Supervised Deep Learning Framework for Learning From Web Data (90 citations)
Self-supervised and contrastive · 3 papers
- Look Into Person: Self-Supervised Structure-Sensitive Learning and a New Benchmark for Human Parsing (532 citations)
- Colorization as a Proxy Task for Visual Understanding (487 citations)
- LSTM Self-Supervision for Detailed Behavior Analysis (51 citations)
Knowledge distillation · 1 paper
- A Gift From Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning (1,664 citations)
Semi-supervised learning · 1 paper
- Learning by Association -- A Versatile Semi-Supervised Training Method for Neural Networks (105 citations)
