Reason induced visual attention for explainable autonomous driving

by   Sikai Chen, et al.

Deep learning (DL) based computer vision (CV) models are generally considered as black boxes due to poor interpretability. This limitation impedes efficient diagnoses or predictions of system failure, thereby precluding the widespread deployment of DLCV models in safety-critical tasks such as autonomous driving. This study is motivated by the need to enhance the interpretability of DL model in autonomous driving and therefore proposes an explainable DL-based framework that generates textual descriptions of the driving environment and makes appropriate decisions based on the generated descriptions. The proposed framework imitates the learning process of human drivers by jointly modeling the visual input (images) and natural language, while using the language to induce the visual attention in the image. The results indicate strong explainability of autonomous driving decisions obtained by focusing on relevant features from visual inputs. Furthermore, the output attention maps enhance the interpretability of the model not only by providing meaningful explanation to the model behavior but also by identifying the weakness of and potential improvement directions for the model.


page 4

page 8

page 11


Development and testing of an image transformer for explainable autonomous driving systems

In the last decade, deep learning (DL) approaches have been used success...

Explainability of vision-based autonomous driving systems: Review and challenges

This survey reviews explainability methods for vision-based self-driving...

Interpretable part-whole hierarchies and conceptual-semantic relationships in neural networks

Deep neural networks achieve outstanding results in a large variety of t...

Explaining Autonomous Driving by Learning End-to-End Visual Attention

Current deep learning based autonomous driving approaches yield impressi...

Towards Explainable AI for Channel Estimation in Wireless Communications

Research into 6G networks has been initiated to support a variety of cri...

Providing Error Detection for Deep Learning Image Classifiers Using Self-Explainability

This paper proposes a self-explainable Deep Learning (SE-DL) system for ...

Please sign up or login with your details

Forgot password? Click here to reset