XC: Exploring Quantitative Use Cases for Explanations in 3D Object Detection
This work addresses the need for automated, quantitative XAI applications in autonomous driving, though it is incremental as it builds on existing gradient-based methods.
The paper tackled the problem of using explainable AI (XAI) methods quantitatively for decision-making in 3D object detection, proposing Explanation Concentration (XC) scores that improved true vs. false positive distinction by over 100% on KITTI and Waymo datasets compared to baselines.
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.