SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.10326 · ICML · 2023

Unsupervised Out-of-Distribution Detection with Diffusion Inpainting

Kilian Weinberger, Zhenzhen Liu, Jin Zhou, Yufan Wang

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 13 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
zhenzhel/lift_map_detect canonical 7 of 13
FunctionStatusWhere it lives
NoneCorrector Ran zhenzhel/lift_map_detect/recon.py
code served (permissive licence) · get_code("9fbf2bcfe266f4eb")
NonePredictor Ran zhenzhel/lift_map_detect/recon.py
code served (permissive licence) · get_code("23801547159a0cde")
get_data_inverse_scaler Ran zhenzhel/lift_map_detect/recon.py
code served (permissive licence) · get_code("6c419026e778dee2")
get_data_scaler Ran zhenzhel/lift_map_detect/recon.py
code served (permissive licence) · get_code("346d2e6cc8b48a5d")
get_pc_inpainter Ran zhenzhel/lift_map_detect/recon.py
code served (permissive licence) · get_code("e9b0be8f6581cb5e")
lpips_scaler Ran zhenzhel/lift_map_detect/detect.py
code served (permissive licence) · get_code("134293ad842ab4e6")
shared_predictor_update_fn Ran zhenzhel/lift_map_detect/recon.py
code served (permissive licence) · get_code("74fd9b4740562d25")
Corrector Not yet run zhenzhel/lift_map_detect/recon.py
code served (permissive licence) · get_code("8d49d40d9988b215")
Detector Not yet run zhenzhel/lift_map_detect/recon.py
code served (permissive licence) · get_code("33bb242d2a46a8af")
Predictor Not yet run zhenzhel/lift_map_detect/recon.py
code served (permissive licence) · get_code("60424db455a86fdc")
get_corrector Not yet run zhenzhel/lift_map_detect/recon.py
code served (permissive licence) · get_code("e476e461754cc223")
shared_corrector_update_fn Not yet run zhenzhel/lift_map_detect/recon.py
code served (permissive licence) · get_code("2fa0834d22aee527")
simclr_resize Not yet run zhenzhel/lift_map_detect/detect.py
code served (permissive licence) · get_code("de5c88ea9339be33")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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 out-of-domain 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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2302.10326")
get_code_for_paper("2302.10326")
have("2302.10326")

Connect an agent — have() is free.