ICCV 2017 accepted papers on Label-efficient and robust learning
80 of the 621 papers accepted at ICCV 2017 (12.9%) are on Label-efficient and robust learning. They fall into 8 topics.
See ICCV 2017 in the interactive map
Submitting to ICCV? 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 · 55 papers
- Interpretable Explanations of Black Boxes by Meaningful Perturbation (1,282 citations)
- Learning Multi-Attention Convolutional Neural Network for Fine-Grained Image Recognition (1,059 citations)
- RGB-Infrared Cross-Modality Person Re-Identification (932 citations)
- Sampling Matters in Deep Embedding Learning (924 citations)
- Pose-Driven Deep Convolutional Model for Person Re-Identification (855 citations)
- Deeply-Learned Part-Aligned Representations for Person Re-Identification (837 citations)
- SVDNet for Pedestrian Retrieval (836 citations)
- HashNet: Deep Learning to Hash by Continuation (799 citations)
- No Fuss Distance Metric Learning Using Proxies (676 citations)
- Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization (610 citations)
- DeepRoadMapper: Extracting Road Topology From Aerial Images (588 citations)
- HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis (588 citations)
and 43 more in the interactive map.
Domain adaptation and generalization · 12 papers
- Deeper, Broader and Artier Domain Generalization (1,352 citations)
- Unified Deep Supervised Domain Adaptation and Generalization (860 citations)
- Open Set Domain Adaptation (576 citations)
- Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes (515 citations)
- AutoDIAL: Automatic DomaIn Alignment Layers (323 citations)
- Associative Domain Adaptation (250 citations)
- Show, Adapt and Tell: Adversarial Training of Cross-Domain Image Captioner (156 citations)
- Fine-Grained Recognition in the Wild: A Multi-Task Domain Adaptation Approach (155 citations)
- Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos (110 citations)
- When Unsupervised Domain Adaptation Meets Tensor Representations (83 citations)
- Domain-Adaptive Deep Network Compression (56 citations)
- PUnDA: Probabilistic Unsupervised Domain Adaptation for Knowledge Transfer Across Visual Categories (48 citations)
Zero-/few-shot and meta-learning · 4 papers
- Low-Shot Visual Recognition by Shrinking and Hallucinating Features (843 citations)
- Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning (176 citations)
- Learning Discriminative Latent Attributes for Zero-Shot Classification (112 citations)
- Attributes2Classname: A Discriminative Model for Attribute-Based Unsupervised Zero-Shot Learning (58 citations)
Self-supervised and contrastive · 3 papers
Semi-supervised learning · 3 papers
- Unlabeled Samples Generated by GAN Improve the Person Re-Identification Baseline in Vitro (2,143 citations)
- Semi Supervised Semantic Segmentation Using Generative Adversarial Network (604 citations)
- Deep Growing Learning (33 citations)
OOD and anomaly detection · 1 paper
Noisy labels · 1 paper
- Learning From Noisy Labels With Distillation (571 citations)
Test-time adaptation · 1 paper
- Predictor Combination at Test Time (3 citations)
