AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

KLIP: Localized Distribution Shift Detection via KL-Divergence with Diffusion Priors in Inverse Problems

Alireza Kheirandish, Jihoon Hong, Sara Fridovich-Keil

CVPR 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add block restriction to raw KL (ablation)D_KL, Predictor-Corrector · CT dataset-level starAUC: 0.54 -> 0.85Improved
add block restriction to raw KL (ablation)D_KL, Predictor-Corrector · CT dataset-level tumorAUC: 0.60 -> 0.65Improved
add block restriction to raw KL (ablation)D_KL, Predictor-Corrector · CT image-level tumorAUC: 0.86 -> 0.91Improved
add timestep restriction to raw KL (ablation)D_KL, Predictor-Corrector · CT dataset-level tumorAUC: 0.60 -> 0.78Improved
add timestep restriction to raw KL (ablation)D_KL, Predictor-Corrector · CT dataset-level starAUC: 0.54 -> 0.57No clear effect
add timestep restriction on top of block restriction (ablation)KLIP, Predictor-Corrector · CT image-level tumorAUC: 0.91 -> 0.88Hurt
add timestep restriction on top of block restriction (ablation)KLIP, Predictor-Corrector · CT dataset-level tumorAUC: 0.65 -> 0.78Improved
tune hyperparameters on tumor set instead of star set (ablation)KLIP, Predictor-Corrector · CT dataset-level starAUC: 0.86 -> 0.68Hurt
tune hyperparameters on tumor set instead of star set (ablation)KLIP, Predictor-Corrector · CT dataset-level tumorAUC: 0.78 -> 0.87Improved
increase Monte Carlo samples from 1 to 8 (ablation)KLIP · CelebA scar image-levelAUC: 0.813 -> 0.904Improved
increase Monte Carlo samples from 8 to 32 (ablation)KLIP · CelebA scar image-levelAUC: 0.904 -> 0.909No clear effect
mismatched reconstruction blur kernel sigma 3 instead of matched 9 (ablation)KLIP · CelebA scar image-levelAUC: 0.904 -> 0.809Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy