Feature Map Convergence Evaluation for Functional Module

TL;DR

This paper introduces a novel evaluation method using feature map analysis to assess the training maturity of functional modules in autonomous driving perception models, enhancing interpretability and optimization.

Contribution

It proposes the first independent evaluation approach for functional modules, including a quantitative metric (FMCS) and a predictive network (FMCE-Net), validated across image classification tasks.

Findings

FMCE-Net accurately predicts FMCS across experiments

The approach improves interpretability of perception models

First independent method for functional module evaluation

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 quantitative metric named as the Feature Map Convergence Score (FMCS) and develop Feature Map Convergence Evaluation Network (FMCE-Net) to measure and predict the convergence degree of models respectively. FMCE-Net achieves remarkable predictive accuracy for FMCS across multiple image classification experiments, validating the efficacy and robustness of the introduced approach. To the best of our knowledge, this is the first independent evaluation method for functional modules, offering a new paradigm for the training assessment towards perception models.