2022 article
CLAIRE: Enabling Continual Learning for Real-time Autonomous Driving with a Dual-head Architecture
2022 IEEE 25TH INTERNATIONAL SYMPOSIUM ON REAL-TIME DISTRIBUTED COMPUTING (ISORC 2022), pp. 51–60.
author keywords: Autonomous Systems; On-board Continual Learning; Real-Time Deep Learning Inference
TL;DR:
A novel lightweight dual-head detection network architecture is proposed to overcome forgetting and to support fast on-board continual learning on small sets of new images and assesses the feasibility of continual learning methods for autonomous driving.
(via Semantic Scholar)
UN Sustainable Development Goal Categories
3. Good Health and Well-being
(Web of Science)
Source: Web Of Science
Added: October 17, 2022
Autonomous vehicles rely on a pre-trained object detector to perceive surroundings. However, when never seen before scenarios are encountered, late decisions may result in hard braking due to perceived threats. Image sequences leading to such a situation provide the potential to learn and improve over time. Yet instant re-training on board with all prior training data is infeasible given computational, storage and power constraints. What’s more, exposure of a pre-trained CNN to only images of the new scenario is known to result in “catastrophic forgetting” for already learned features.This work makes several contributions: A novel lightweight dual-head detection network architecture is proposed to overcome forgetting and to support fast on-board continual learning on small sets of new images and assesses the feasibility of continual learning methods for autonomous driving. A sensitivity study on the quality and quantity of continually learned images for our dual-head technique is performed, including an assessment of its real-time suitability. Experiments show that our method’s accuracy is improved by up to 13% and performance increases by 5.8X over a state-of-the-art continual learning framework. This makes it suitable for autonomous driving scenarios with real-time constraints. Source code is made available via Github.