Aggregated Sparse Attention for Steering Angle Prediction

03/15/2018

∙

by Sen He, et al.

∙

University of Exeter

∙

In this paper, we apply the attention mechanism to autonomous driving for steering angle prediction. We propose the first model, applying the recently introduced sparse attention mechanism to visual domain, as well as the aggregated extension for this model. We show the improvement of the proposed method, comparing to no attention as well as to different types of attention.

READ FULL TEXT

Aggregated Sparse Attention for Steering Angle Prediction

Linear Attention Mechanism: An Efficient Attention for Semantic Segmentation

Text Classification with Lexicon from PreAttention Mechanism

Link Prediction with Mutual Attention for Text-Attributed Networks

Dynamic N:M Fine-grained Structured Sparse Attention Mechanism

Towards Greener Solutions for Steering Angle Prediction

Attention Mechanism in Neural Networks: Where it Comes and Where it Goes

Supervised Domain Enablement Attention for Personalized Domain Classification

Aggregated Sparse Attention for Steering Angle Prediction

Related Research

Linear Attention Mechanism: An Efficient Attention for Semantic Segmentation

Text Classification with Lexicon from PreAttention Mechanism

Link Prediction with Mutual Attention for Text-Attributed Networks

Dynamic N:M Fine-grained Structured Sparse Attention Mechanism

Towards Greener Solutions for Steering Angle Prediction

Attention Mechanism in Neural Networks: Where it Comes and Where it Goes

Supervised Domain Enablement Attention for Personalized Domain Classification