Eloss in the way: A Sensitive Input Quality Metrics for Intelligent Driving

TL;DR

This paper introduces Eloss, a novel metric for intelligent driving perception models that detects anomalies by analyzing information compression layers, improving safety perception in complex traffic environments.

Contribution

The paper proposes Eloss, a new anomaly detection metric based on information theory, and a training strategy to enhance perception models for better safety in diverse driving conditions.

Findings

Eloss deviates significantly with anomalous data, over 100 times from standard value.

Eloss produces distinctive values for different types of anomalies.

The method improves anomaly detection sensitivity in perception models.

Abstract

With the increasing complexity of the traffic environment, the importance of safety perception in intelligent driving is growing. Conventional methods in the robust perception of intelligent driving focus on training models with anomalous data, letting the deep neural network decide how to tackle anomalies. However, these models cannot adapt smoothly to the diverse and complex real-world environment. This paper proposes a new type of metric known as Eloss and offers a novel training strategy to empower perception models from the aspect of anomaly detection. Eloss is designed based on an explanation of the perception model's information compression layers. Specifically, taking inspiration from the design of a communication system, the information transmission process of an information compression network has two expectations: the amount of information changes steadily, and the information entropy continues to decrease. Then Eloss can be obtained according to the above expectations, guiding the update of related network parameters and producing a sensitive metric to identify anomalies while maintaining the model performance. Our experiments demonstrate that Eloss can deviate from the standard value by a factor over 100 with anomalous data and produce distinctive values for similar but different types of anomalies, showing the effectiveness of the proposed method. Our code is available at: (code available after paper accepted).