2024-09-12-arnez24a.md

title	abstract	openreview	software	section	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Latent Representation Entropy Density for Distribution Shift Detection	Distribution shift detection is paramount in safety-critical tasks that rely on Deep Neural Networks (DNNs). The detection task entails deriving a confidence score to assert whether a new input sample aligns with the training data distribution of the DNN model. While DNN predictive uncertainty offers an intuitive confidence measure, exploring uncertainty-based distribution shift detection with simple sample-based techniques has been relatively overlooked in recent years due to computational overhead and lower performance than plain post-hoc methods. This paper proposes using simple sample-based techniques for estimating uncertainty and employing the entropy density from intermediate representations to detect distribution shifts. We demonstrate the effectiveness of our method using standard benchmark datasets for out-of-distribution detection and across different common perception tasks with convolutional neural network architectures. Our scope extends beyond classification, encompassing image-level distribution shift detection for object detection and semantic segmentation tasks. Our results show that our method’s performance is comparable to existing <em>State-of-the-Art</em> methods while being computationally faster and lighter than other Bayesian approaches, affirming its practical utility.	1CKLfh3Ge7	https://github.com/CEA-LIST/LaREx	Papers	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	arnez24a	0	Latent Representation Entropy Density for Distribution Shift Detection	110	137	110-137	110	false	Arnez, Fabio and Montoya Vasquez, Daniel Alfonso and Radermacher, Ansgar and Terrier, Fran\c{c}ois	given family Fabio Arnez given family Daniel Alfonso Montoya Vasquez given family Ansgar Radermacher given family François Terrier	2024-09-12		Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence	244	inproceedings	date-parts 2024 9 12	https://raw.githubusercontent.com/mlresearch/v244/main/assets/arnez24a/arnez24a.pdf