Recently, it has been demonstrated that the performance of a deep convolutional neural network can be effectively improved by embedding an attention module into it.
We challenge a common assumption underlying most supervised deep learning: that a model makes a prediction depending only on its parameters and the features of a single input.
This paper presents a simple yet effective approach to modeling space-time correspondences in the context of video object segmentation.
Ranked #1 on Semi-Supervised Video Object Segmentation on DAVIS 2017 (val) (using extra training data)
Multi-Agent Reinforcement Learning (MARL) has seen revolutionary breakthroughs with its successful application to multi-agent cooperative tasks such as computer games and robot swarms.
We devise a hybrid deep learning approach to solving tabular data problems.
In particular, we present Decision Transformer, an architecture that casts the problem of RL as conditional sequence modeling.
Ranked #1 on Atari Games on Atari 2600 Pong