Feature Map Convergence Evaluation for Functional Module
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous Drivingimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Decoupled Functional Evaluation of Autonomous Driving Models via Feature Map Quality Scoring
End-to-end models are emerging as the mainstream in autonomous driving perception and planning. However, the lack of explicit supervision signals for intermediate functional modules leads to opaque operational mechanisms…
3D Object DetectionAutonomous DrivingUnveiling the Black Box: Independent Functional Module Evaluation for Bird's-Eye-View Perception Model
End-to-end models are emerging as the mainstream in autonomous driving perception. However, the inability to meticulously deconstruct their internal mechanisms results in diminished development efficacy and impedes the e…
Autonomous DrivingFMCE-Net++: Feature Map Convergence Evaluation and Training
Deep Neural Networks (DNNs) face interpretability challenges due to their opaque internal representations. While Feature Map Convergence Evaluation (FMCE) quantifies module-level convergence via Feature Map Convergence S…
Checking Functional Modularity in DNN By Biclustering Task-specific Hidden Neurons
While real brain networks exhibit functional modularity, we investigate whether functional mod- ularity also exists in Deep Neural Networks (DNN) trained through back-propagation. Under the hypothesis that DNN are also o…
Federated Functional Gradient Boosting
In this paper, we initiate a study of functional minimization in Federated Learning. First, in the semi-heterogeneous setting, when the marginal distributions of the feature vectors on client machines are identical, we d…
Federated Learning