CLAD: A realistic Continual Learning benchmark for Autonomous Driving. (April 2023)

• Record Type: Journal Article
• Authors: Verwimp, Eli; Yang, Kuo; Parisot, Sarah; Hong, Lanqing; McDonagh, Steven; Pérez-Pellitero, Eduardo; De Lange, Matthias; Tuytelaars, Tinne
• Is Part Of: Neural networks. Volume 161(2023)
• Page Start: 659
• Page End: 669
• Publication Date: 2023-04
• Subjects: Continual learning -- Classification -- Object detection -- Challenge report -- Benchmark; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2023.02.001
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: In this paper we describe the design and the ideas motivating a new Continual Learning benchmark for Autonomous Driving (CLAD), that focuses on the problems of object classification and object detection. The benchmark utilises SODA10M, a recently released large-scale dataset that concerns autonomous driving related problems. First, we review and discuss existing continual learning benchmarks, how they are related, and show that most are extreme cases of continual learning. To this end, we survey the benchmarks used in continual learning papers at three highly ranked computer vision conferences. Next, we introduce CLAD-C, an online classification benchmark realised through a chronological data stream that poses both class and domain incremental challenges; and CLAD-D, a domain incremental continual object detection benchmark. We examine the inherent difficulties and challenges posed by the benchmark, through a survey of the techniques and methods used by the top-3 participants in a CLAD-challenge workshop at ICCV 2021. We conclude with possible pathways to improve the current continual learning state of the art, and which directions we deem promising for future research. Highlights: A review of current continual learning benchmarks and their relations to one-another. Proposal of two new real-world continual learning benchmarks. Review of the most successful ICCV'21 challenge entries on the new benchmarks.