XC: Exploring Quantitative Use Cases for Explanations in 3D Object Detection

TL;DR

This paper introduces XC scores, a quantitative measure for explanations in 3D object detection, enabling automated decision-making and outperforming heuristic methods in distinguishing true positives from false positives.

Contribution

The paper proposes XC scores based on gradient explanations for 3D detection, demonstrating their effectiveness in downstream tasks and challenging the necessity of complex XAI methods.

Findings

XC scores improve TP/FP distinction by over 100% on KITTI and Waymo datasets.

Simpler explanation methods can be as effective as complex ones like Integrated Gradients.

XC scores facilitate automated decision-making in 3D object detection.

Abstract

Explainable AI (XAI) methods are frequently applied to obtain qualitative insights about deep models' predictions. However, such insights need to be interpreted by a human observer to be useful. In this paper, we aim to use explanations directly to make decisions without human observers. We adopt two gradient-based explanation methods, Integrated Gradients (IG) and backprop, for the task of 3D object detection. Then, we propose a set of quantitative measures, named Explanation Concentration (XC) scores, that can be used for downstream tasks. These scores quantify the concentration of attributions within the boundaries of detected objects. We evaluate the effectiveness of XC scores via the task of distinguishing true positive (TP) and false positive (FP) detected objects in the KITTI and Waymo datasets. The results demonstrate an improvement of more than 100\% on both datasets compared to other heuristics such as random guesses and the number of LiDAR points in the bounding box, raising confidence in XC's potential for application in more use cases. Our results also indicate that computationally expensive XAI methods like IG may not be more valuable when used quantitatively compare to simpler methods.