Towards Better Explanations for Object Detection

Van Binh Truong, Truong Thanh Hung Nguyen, Vo Thanh Khang Nguyen, Quoc Khanh Nguyen, Quoc Hung Cao
Proceedings of the 15th Asian Conference on Machine Learning, PMLR 222:1385-1400, 2024.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v222-truong24a, title = {Towards Better Explanations for Object Detection}, author = {Truong, Van Binh and Nguyen, Truong Thanh Hung and Nguyen, Vo Thanh Khang and Nguyen, Quoc Khanh and Cao, Quoc Hung}, booktitle = {Proceedings of the 15th Asian Conference on Machine Learning}, pages = {1385--1400}, year = {2024}, editor = {Yanıkoğlu, Berrin and Buntine, Wray}, volume = {222}, series = {Proceedings of Machine Learning Research}, month = {11--14 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v222/truong24a/truong24a.pdf}, url = {https://proceedings.mlr.press/v222/truong24a.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Towards Better Explanations for Object Detection %A Van Binh Truong %A Truong Thanh Hung Nguyen %A Vo Thanh Khang Nguyen %A Quoc Khanh Nguyen %A Quoc Hung Cao %B Proceedings of the 15th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Berrin Yanıkoğlu %E Wray Buntine %F pmlr-v222-truong24a %I PMLR %P 1385--1400 %U https://proceedings.mlr.press/v222/truong24a.html %V 222 %X 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.
APA
Truong, V.B., Nguyen, T.T.H., Nguyen, V.T.K., Nguyen, Q.K. & Cao, Q.H.. (2024). Towards Better Explanations for Object Detection. Proceedings of the 15th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 222:1385-1400 Available from https://proceedings.mlr.press/v222/truong24a.html.

Related Material