An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

Abstract

Although deep neural networks enable impressive visual perception performance for autonomous driving, their robustness to varying weather conditions still requires attention. When adapting these models for changed environments, such as different weather conditions, they are prone to forgetting previously learned information. This catastrophic forgetting is typically addressed via incremental learning approaches which usually re-train the model by either keeping a memory bank of training samples or keeping a copy of the entire model or model parameters for each scenario. While these approaches show impressive results, they can be prone to scalability issues and their applicability for autonomous driving in all weather conditions has not been shown. In this paper we propose DISC -- Domain Incremental through Statistical Correction -- a simple online zero-forgetting approach which can incrementally learn new tasks (i.e weather conditions) without requiring re-training or expensive memory banks. The only information we store for each task are the statistical parameters as we categorize each domain by the change in first and second order statistics. Thus, as each task arrives, we simply 'plug and play' the statistical vectors for the corresponding task into the model and it immediately starts to perform well on that task. We show the efficacy of our approach by testing it for object detection in a challenging domain-incremental autonomous driving scenario where we encounter different adverse weather conditions, such as heavy rain, fog, and snow.
Original languageEnglish
Title of host publication2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Pages3000-3010
ISBN (Electronic)978-1-6654-8739-9
DOIs
Publication statusPublished - 2022
Event2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops: Vision for All Seasons: Adverse Weather and Lighting Conditions Workshop: CVPRW 2022 - Hybrider Event, United States
Duration: 20 Jun 2022 → …

Workshop

Workshop2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops: Vision for All Seasons: Adverse Weather and Lighting Conditions Workshop
Abbreviated titleCVPRW 2022
Country/TerritoryUnited States
CityHybrider Event
Period20/06/22 → …

Fingerprint

Dive into the research topics of 'An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions'. Together they form a unique fingerprint.

Cite this