Res2Net: A New Multi-scale Backbone Architecture
CE-Net: Context Encoder Network for 2D Medical Image Segmentation
Mixed Precision Training
BitTrain: Sparse Bitmap Compression for Memory-Efficient Training on the Edge
Massively Multilingual Neural Machine Translation
Adversarial NLI: A New Benchmark for Natural Language Understanding
Webly Supervised Joint Embedding for Cross-Modal Image-Text Retrieval
TextBoxes++: A Single-Shot Oriented Scene Text Detector
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
Robust Optimization for Multilingual Translation with Imbalanced Data
Making Pre-trained Language Models Better Few-shot Learners
Whitening Sentence Representations for Better Semantics and Faster Retrieval
Deep Fragment Embeddings for Bidirectional Image Sentence Mapping
K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
Deep learning for cardiac image segmentation: A review
Deep Directed Generative Autoencoders
Adversarial Representation Learning for Robust Privacy Preservation in\n Audio
Ecological Consequences of Trophic Cascades: A Global Perspective
