AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Inferring and Leveraging Parts From Object Shape for Improving Semantic Image Synthesis

Yuxiang Wei, Zhilong Ji, Xiaohe Wu, Jinfeng Bai, Lei Zhang, Wangmeng Zuo

CVPR 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 3 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
add global adversarial loss to the OASIS baseline (ablation)semantic image synthesis · CityscapesFID: 47.7 -> 43.6Improved
add object-level CLIP style loss after global adversarial loss (ablation)semantic image synthesis · CityscapesFID: 43.6 -> 42.8Improved
add inferred parts and sequential PSM to the loss-augmented model (ablation)semantic image synthesis · Cityscapesobj FID: 37.5 -> 30.4Improved
replace sequential PSM with SPADE part injection (ablation)iPOSE · CityscapesFID: 41.3 -> 42.9Hurt
replace sequential PSM with concatenation part injection (ablation)iPOSE · CityscapesFID: 41.3 -> 42.7Hurt
replace object-level CLIP style loss with VGG loss (ablation)iPOSE · CityscapesFID: 41.3 -> 41.6Hurt
increase support maps from 1 to 3 (ablation)PartNet · novel part categoriesAC: 81.41 -> 85.00Improved
increase support maps from 1 to 3 (ablation)PartNet-powered synthesis · COCOFID: 15.76 -> 15.72Improved
add a multi-scale encoder (ablation)PartNet · novel part categoriesAC: 83.21 -> 85.00Improved
increase cross-attention blocks from 1 to 3 (ablation)PartNet · novel part categoriesAC: 82.28 -> 85.00Improved
increase cross-attention blocks from 3 to 4 (ablation)PartNet · novel part categoriesAC: 85.00 -> 83.41Hurt
replace predicted part maps with ground-truth part maps (ablation)iPOSE · CityscapesFID: 41.3 -> 40.8Improved

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