Group Regression for Query Based Object Detection and Tracking

TL;DR

This paper introduces a multi-class group regression method for 3D object detection and tracking in autonomous driving, enhancing transformer-based models by dividing classes into groups for improved performance.

Contribution

It presents a novel approach to multi-class group regression tailored for query-based perception models in 3D detection and tracking, which was previously not feasible.

Findings

Applicable to existing transformer-based perception methods

Improves class-specific regression accuracy

Provides insights into class-switching behavior

Abstract

Group regression is commonly used in 3D object detection to predict box parameters of similar classes in a joint head, aiming to benefit from similarities while separating highly dissimilar classes. For query-based perception methods, this has, so far, not been feasible. We close this gap and present a method to incorporate multi-class group regression, especially designed for the 3D domain in the context of autonomous driving, into existing attention and query-based perception approaches. We enhance a transformer based joint object detection and tracking model with this approach, and thoroughly evaluate its behavior and performance. For group regression, the classes of the nuScenes dataset are divided into six groups of similar shape and prevalence, each being regressed by a dedicated head. We show that the proposed method is applicable to many existing transformer based perception approaches and can bring potential benefits. The behavior of query group regression is thoroughly analyzed in comparison to a unified regression head, e.g. in terms of class-switching behavior and distribution of the output parameters. The proposed method offers many possibilities for further research, such as in the direction of deep multi-hypotheses tracking.