AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

AnyPattern: Towards In-context Image Copy Detection

Wenhao Wang, Yifan Sun, Zhentao Tan, Yi Yang

IJCV 2026 · Image generation › Text-to-image diffusion · approach: Multi-subject personalization · 7 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
train on 90-pattern AnyPattern instead of SmallPatternBaseline · novel patternsuAP: 16.18 -> 42.84Improved
add in-context ImageStacker promptingBaseline · novel patternsuAP: 42.84 -> 56.65Improved
add in-context ImageStacker promptingBaseline · base patternsuAP: 79.37 -> 83.56Improved
add ImageStacker when training on SmallPattern with ImageNetBaseline · novel patternsuAP: 16.18 -> 15.28No clear effect
train ImageStacker on AnyPattern without ImageNet pretraining (ablation)ImageStacker · novel patternsuAP: 40.52 -> 53.53Improved
use in-context learning instead of fine-tuning on 2,400 imagesImageStacker · novel patternsuAP: 41.15 -> 56.65Improved
fine-tune on 200,000 novel-pattern images instead of in-contextImageStacker · base patternsuAP: 83.56 -> 20.06Hurt
stack pair on channel dimension instead of concatenating (ImageCombiner) (ablation)ImageStacker · novel patternsuAP: 48.47 -> 56.65Improved
stack pair on channel dimension instead of adding to replica (ImageAdder) (ablation)ImageStacker · novel patternsuAP: 25.07 -> 56.65Improved
feature-level integration of pair instead of image-level stacking (ablation)ImageStacker · novel patternsuAP: 37.42 -> 56.65Improved
retrieve prompt by pattern retrieval instead of random (ablation)ImageStacker · novel patternsuAP: 50.42 -> 56.65Improved
use ground-truth pattern pair instead of retrieved pair (ablation)ImageStacker · novel patternsuAP: 56.65 -> 56.99No clear effect

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