Recognition, Classification, Clustering, Retrieval
- [x] DocFace+: ID Document to Selfie Matching
- [ ] Improving Face Recognition by Exploring Local Features with Visual Attention
- [ ] Face Clustering: Representation and Pairwise Constraints
- [ ] Face Recognition: Primates in the Wild
- [x] RegularFace: Deep Face Recognition via Exclusive Regularization
- [x] UniformFace, Equidistributed Representation for Face Recognition
- [x] Video Face Recognition: Component-wise Feature Aggregation Network (C-FAN)
- [ ] Decorrelated Adversarial Learning for Age-Invariance Face Recognition
- [ ] Center Loss
- [ ] Learning Invariant Deep Representation for NIR-VIS Face Recognition
- [ ] Transferring deep representation for NIR-VIS heterogeneous face recognition
Detection, Segmentation
- [ ] YOLO
- [ ] YOLO V2
- [ ] YOLO V3
- [ ] SSD
- [x] Feature Pyramid Networks for Object Detection
- [ ] Non-Local Neural Networks
Network Architecture
- [x] Deep High-Resolution Representation Learning for Human Pose Estimation (HRNet)
- [ ] SENet
- [ ] High-Resolution Representations for Labeling Pixels and Regions (HRNet V2)
- [ ] PolyNet: A Pursuit of Structural Diversity in Very Deep Networks (PolyNet)
Optimization / Training Scheme
- [ ] Adversarial Examples Are Not Bugs, They Are Features
Related blog, thread / discussion.
Probability Theory, Machine Learning
- [ ] Discriminating Between the Normal and the Lablace Distributions
- [ ] Reconciling Modern Machine Learning and the Bias-Variance Trade-off
- [ ] To understand deep learning we need to understand kernel learning
- [ ] Introduction to RKHS, and some simple kernel algorithms
- [ ] A Primer on Reproducing Kernel Hilbert Spaces
- [ ] A Training Algorithm for Optimal Margin Classiers