Unsupervised Out-of-Distribution Detection with Diffusion Inpainting

Zhenzhen Liu, Jin Peng Zhou, Yufan Wang, Kilian Q Weinberger
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22528-22538, 2023.

Abstract

Unsupervised out-of-distribution detection (OOD) seeks to identify out-of-domain data by learning only from unlabeled in-domain data. We present a novel approach for this task – Lift, Map, Detect (LMD) – that leverages recent advancement in diffusion models. Diffusion models are one type of generative models. At their core, they learn an iterative denoising process that gradually maps a noisy image closer to their training manifolds. LMD leverages this intuition for OOD detection. Specifically, LMD lifts an image off its original manifold by corrupting it, and maps it towards the in-domain manifold with a diffusion model. For an OOD image, the mapped image would have a large distance away from its original manifold, and LMD would identify it as OOD accordingly. We show through extensive experiments that LMD achieves competitive performance across a broad variety of datasets. Code can be found at https://github.com/zhenzhel/lift_map_detect.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-liu23bd, title = {Unsupervised Out-of-Distribution Detection with Diffusion Inpainting}, author = {Liu, Zhenzhen and Zhou, Jin Peng and Wang, Yufan and Weinberger, Kilian Q}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {22528--22538}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/liu23bd/liu23bd.pdf}, url = {https://proceedings.mlr.press/v202/liu23bd.html}, abstract = {Unsupervised out-of-distribution detection (OOD) seeks to identify out-of-domain data by learning only from unlabeled in-domain data. We present a novel approach for this task – Lift, Map, Detect (LMD) – that leverages recent advancement in diffusion models. Diffusion models are one type of generative models. At their core, they learn an iterative denoising process that gradually maps a noisy image closer to their training manifolds. LMD leverages this intuition for OOD detection. Specifically, LMD lifts an image off its original manifold by corrupting it, and maps it towards the in-domain manifold with a diffusion model. For an OOD image, the mapped image would have a large distance away from its original manifold, and LMD would identify it as OOD accordingly. We show through extensive experiments that LMD achieves competitive performance across a broad variety of datasets. Code can be found at https://github.com/zhenzhel/lift_map_detect.} }
Endnote
%0 Conference Paper %T Unsupervised Out-of-Distribution Detection with Diffusion Inpainting %A Zhenzhen Liu %A Jin Peng Zhou %A Yufan Wang %A Kilian Q Weinberger %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-liu23bd %I PMLR %P 22528--22538 %U https://proceedings.mlr.press/v202/liu23bd.html %V 202 %X Unsupervised out-of-distribution detection (OOD) seeks to identify out-of-domain data by learning only from unlabeled in-domain data. We present a novel approach for this task – Lift, Map, Detect (LMD) – that leverages recent advancement in diffusion models. Diffusion models are one type of generative models. At their core, they learn an iterative denoising process that gradually maps a noisy image closer to their training manifolds. LMD leverages this intuition for OOD detection. Specifically, LMD lifts an image off its original manifold by corrupting it, and maps it towards the in-domain manifold with a diffusion model. For an OOD image, the mapped image would have a large distance away from its original manifold, and LMD would identify it as OOD accordingly. We show through extensive experiments that LMD achieves competitive performance across a broad variety of datasets. Code can be found at https://github.com/zhenzhel/lift_map_detect.
APA
Liu, Z., Zhou, J.P., Wang, Y. & Weinberger, K.Q.. (2023). Unsupervised Out-of-Distribution Detection with Diffusion Inpainting. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:22528-22538 Available from https://proceedings.mlr.press/v202/liu23bd.html.

Related Material