Computer Vision (37)
- A Discriminative Feature Learning Approach for Deep Face Recognition
- Adaptive Dropout for Training Deep Neural Networks
- Aggregated Residual Transformation for Deep Neural Networks
- Annealed Dropout Training of Deep Networks
- Class-Balanced Loss Based on Effective Number of Samples
- Deep Learning
- Deep Networks with Stochastic Depth
- Deep Subspace Clustering Netoworks
- DropoutNet: Addressing Cold Start in Recommender Systems
- Dynamic Routing Between Capsules
- Few-Shot Adversarial Domain Adaption
- Grad-CAM: Why did you say that? Visual Explanations from Deep Networks via Gradient-based Localization
- ImageNet Classification with Deep Convolutional Neural Networks
- Improving neural networks by preventing co-adaptation of feature detectors
- Inductive Bias of Deep Convolutional Networks through Pooling Geometry
- Learn to Pay Attention
- Learning Deep Classifiers with Deep Features
- Max-Pooling Dropout for Regularization of Convolutional Neural Networks
- Multi-Modal Fashion Product Retrieval
- Noisy Softmax: Improving the Generalization Ability of DCNN via Postponing the Early Softmax Saturation
- Random Erasing Data Augmentation
- Realistic Evaluation of Semi-Supervised Learning Algorithms
- Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization
- Robust Convolutional Neural Networks Under Adversarial Noise
- SC-FEGAN: Face Editing Generative Adversarial Networks with User's Sketch and Color
- SVD-Softmax: Fast Softmax Approximation on Large Vocabulary Neural Networks
- Semi-supervised Deep Learning by Metric Embedding
- Signiture Verification using a "Siamese" Time Delay Neural Network
- Sparse Embedded k-Means Clustering
- SpectralNet: Spectral Clustering Using Deep Neural Networks
- Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction
- Style2Vec: Representation Learning for Fashion Items from Style Sets
- Tell Me Where to Look: Guided Attention Inference Network
- Unsupervised Deep Embedding for Clustering Analysis
- Visualizing and Understanding Convolutional Networks
- Wide Residual Networks
- You Only Look Once: Unified, Real-Time Object Detection