Towards Better Explanations for Object Detection
This addresses the need for interpretability in object detection for AI practitioners, but it is incremental as it builds on existing explanation techniques.
The paper tackles the problem of explaining object detection models, which are less studied than classification, by proposing D-CLOSE, a method that uses multi-level segmentation to track model behavior, resulting in better quality and less noise explanations compared to D-RISE on the MS-COCO dataset with YOLOX.
Recent advances in Artificial Intelligence (AI) technology have promoted their use in almost every field. The growing complexity of deep neural networks (DNNs) makes it increasingly difficult and important to explain the inner workings and decisions of the network. However, most current techniques for explaining DNNs focus mainly on interpreting classification tasks. This paper proposes a method to explain the decision for any object detection model called D-CLOSE. To closely track the model's behavior, we used multiple levels of segmentation on the image and a process to combine them. We performed tests on the MS-COCO dataset with the YOLOX model, which shows that our method outperforms D-RISE and can give a better quality and less noise explanation.