Unveiling the Black Box: Independent Functional Module Evaluation for Bird's-Eye-View Perception Model
This addresses the issue of trust and development efficiency in autonomous driving perception for researchers and engineers, representing an incremental improvement in evaluation methods.
The paper tackles the problem of evaluating internal functional modules in end-to-end autonomous driving perception models by proposing BEV-IFME, a framework that quantifies module training maturity using similarity scores, achieving an average correlation coefficient of 0.9387 with BEV metrics.
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 establishment of trust. Pioneering in the issue, we present the Independent Functional Module Evaluation for Bird's-Eye-View Perception Model (BEV-IFME), a novel framework that juxtaposes the module's feature maps against Ground Truth within a unified semantic Representation Space to quantify their similarity, thereby assessing the training maturity of individual functional modules. The core of the framework lies in the process of feature map encoding and representation aligning, facilitated by our proposed two-stage Alignment AutoEncoder, which ensures the preservation of salient information and the consistency of feature structure. The metric for evaluating the training maturity of functional modules, Similarity Score, demonstrates a robust positive correlation with BEV metrics, with an average correlation coefficient of 0.9387, attesting to the framework's reliability for assessment purposes.