We propose spatially-adaptive normalization, a simple but effective layer for synthesizing photorealistic images given an input semantic layout.
We compare Dragonfly to a suite of other packages and algorithms for global optimisation and demonstrate that when the above methods are integrated, they enable significant improvements in the performance of BO.
In this paper, we present a Multi-Task Deep Neural Network (MT-DNN) for learning representations across multiple natural language understanding (NLU) tasks.
SOTA for Natural Language Inference on SNLI
We propose a new bottom-up method for multi-person 2D human pose estimation that is particularly well suited for urban mobility such as self-driving cars and delivery robots.
In the literature, some effective training tricks are briefly appeared in several papers or source codes.
In this work we adapt multi-person pose estimation architecture to use it on edge devices.
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration.
Recent interest in graph embedding methods has focused on learning a single representation for each node in the graph.
We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers.
SOTA for Common Sense Reasoning on SWAG