Feature Map Convergence Evaluation for Functional Module

arXiv:2405.04041v1 Announce Type: cross
Abstract: Autonomous driving perception models are typically composed of multiple functional modules that interact through complex relationships to accomplish environment understanding. However, perception models are predominantly optimized as a black box through end-to-end training, lacking independent evaluation of functional modules, which poses difficulties for interpretability and optimization. Pioneering in the issue, we propose an evaluation method based on feature map analysis to gauge the convergence of model, thereby assessing functional modules' training maturity. We construct a …

abstract arxiv autonomous autonomous driving black box box convergence cs.ai cs.cv driving environment evaluation feature functional however independent interpretability map modules multiple optimization perception relationships through training type understanding