# Feature Map Convergence Evaluation for Functional Module

arXiv: https://arxiv.org/abs/2405.04041 · HTML: https://mlsanity.com/paper/2405.04041/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 24 references that are in the map.
- First posted on arXiv 7 May 2024.

## Builds on (most cited first, 14 of 14)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Neural Module Networks](https://mlsanity.com/paper/1511.02799/) (2015)
- [PathNet: Evolution Channels Gradient Descent in Super Neural Networks](https://mlsanity.com/paper/1701.08734/) (2017)
- [BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision](https://mlsanity.com/paper/2211.10439/) (2022)
- [Explainability of deep vision-based autonomous driving systems: Review and challenges](https://mlsanity.com/paper/2101.05307/) (2021)
- [Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review](https://mlsanity.com/paper/2402.10086/) (2024)
- [Shapley Explanation Networks](https://mlsanity.com/paper/2104.02297/) (2021)
- [Shap-CAM: Visual Explanations for Convolutional Neural Networks based on Shapley Value](https://mlsanity.com/paper/2208.03608/) (2022)
- [CLIP-BEVFormer: Enhancing Multi-View Image-Based BEV Detector with Ground Truth Flow](https://mlsanity.com/paper/2403.08919/) (2024)
- [GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector](https://mlsanity.com/paper/2205.15469/) (2022)
- [Boosting Monocular 3D Object Detection with Object-Centric Auxiliary Depth Supervision](https://mlsanity.com/paper/2210.16574/) (2022)
- [Quantitative Performance Assessment of CNN Units via Topological Entropy Calculation](https://mlsanity.com/paper/2103.09716/) (2021)

## Built on by (most cited first, 6 of 6)

- [Hierarchical and Decoupled BEV Perception Learning Framework for Autonomous Driving](https://mlsanity.com/paper/2407.12491/) (2024)
- [Unveiling the Black Box: Independent Functional Module Evaluation for Bird's-Eye-View Perception Model](https://mlsanity.com/paper/2409.11969/) (2024)
- [RNN as Linear Transformer: A Closer Investigation into Representational Potentials of Visual Mamba Models](https://mlsanity.com/paper/2511.18380/) (2025)
- [Hierarchical Feature-level Reverse Propagation for Post-Training Neural Networks](https://mlsanity.com/paper/2506.07188/) (2025)
- [FMCE-Net++: Feature Map Convergence Evaluation and Training](https://mlsanity.com/paper/2508.06109/) (2025)
- [Decoupled Functional Evaluation of Autonomous Driving Models via Feature Map Quality Scoring](https://mlsanity.com/paper/2508.07552/) (2025)

## Abstract (arXiv)

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.