AI Paper Atlas

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

MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentation

Jiahao Xie, Wei Li, Xiangtai Li, Ziwei Liu, Yew-Soon Ong, Chen Change Loy

IJCV 2024 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 48 citations (OpenAlex)

Read the paper

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
increase generated objects per image from 1 to 4 (ablation)MosaicFusion Mask R-CNN · LVIS v1.0 val (Mask R-CNN R50-FPN ablations)mask AP_r: 14.0 -> 15.2Improved
add synthetic MosaicFusion data to Mask R-CNNMask R-CNN R50 · LVIS v1.0 val (long-tailed)mask AP_r: 9.6 -> 15.2Improved
add MosaicFusion data to Box-Supervised CenterNet2 Swin-BCenterNet2 · LVIS v1.0 val (long-tailed)mask AP_r: 35.9 -> 39.0Improved
add MosaicFusion to F-VLM R50x64 on open-vocabulary LVISF-VLM · LVIS open-vocabulary valAP novel: 31.7 -> 34.9Improved
add MosaicFusion to Co-DETR Swin-LCo-DETR · LVIS valbox AP_r: 61.4 -> 64.4Improved
add MosaicFusion to F-VLM R50x64 on V3DetF-VLM · V3Det open-vocabulary valbox AP novel: 7.0 -> 14.5Improved
generate multi-object images directly instead of Mosaic augmentation of single-object images (ablation)MosaicFusion · LVIS v1.0 val (Mask R-CNN R50-FPN ablations)mask AP_r: 14.0 -> 15.2Improved
add category definition to text prompt (ablation)MosaicFusion · LVIS v1.0 val (Mask R-CNN R50-FPN ablations)mask AP_r: 13.5 -> 15.2Improved
moderate region overlap (64,48) instead of none (ablation)MosaicFusion · LVIS v1.0 val (Mask R-CNN R50-FPN ablations)mask AP_r: 14.2 -> 15.2Improved
larger region overlap (128,96) (ablation)MosaicFusion · LVIS v1.0 val (Mask R-CNN R50-FPN ablations)mask AP_r: 15.2 -> 13.2Hurt
generate all categories instead of rare only (ablation)MosaicFusion · LVIS v1.0 val (Mask R-CNN R50-FPN ablations)mask AP_r: 14.2 -> 15.2Improved
generate 50 instead of 25 images per category (ablation)MosaicFusion · LVIS v1.0 val (Mask R-CNN R50-FPN ablations)mask AP_r: 15.2 -> 14.7No 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