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