AI Paper Atlas

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

ManiCLIP: Multi-attribute Face Manipulation from Text

Hao Wang, Guosheng Lin, Ana García del Molino, Anran Wang, Jiashi Feng, Zhiqi Shen

IJCV 2024 · Image generation › Text-to-image diffusion · approach: Multi-subject personalization · 13 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 decoupling training (group sampling) to the baseline (ablation)ManiCLIP · Multi-Modal-CelebA-HQ test (5,000)FID: 40.70 -> 34.60Improved
add entropy loss to the baseline (ablation)ManiCLIP · Multi-Modal-CelebA-HQ test (5,000)FID: 40.70 -> 38.62Improved
add entropy loss to decoupling training (ablation)ManiCLIP · Multi-Modal-CelebA-HQ test (5,000)FID: 34.60 -> 31.57Improved
add decoupling training to entropy-loss model (ablation)ManiCLIP · Multi-Modal-CelebA-HQ test (5,000)FID: 38.62 -> 31.57Improved
add decoupling training to the baseline (ablation)ManiCLIP · Multi-Modal-CelebA-HQ test (5,000)ID similarity: 69.88 -> 74.41Improved
add entropy loss to the baseline (ablation)ManiCLIP · Multi-Modal-CelebA-HQ test (5,000)ID similarity: 69.88 -> 73.24Improved
add entropy loss to the baseline (ablation)ManiCLIP · Multi-Modal-CelebA-HQ test (5,000)attribute accuracy: 83.60 -> 84.73Improved
add decoupling training to the baseline (ablation)ManiCLIP · Multi-Modal-CelebA-HQ test (5,000)attribute accuracy: 83.60 -> 84.38Improved
use group sampling instead of random sampling at Na=3 (ablation)ManiCLIP · Multi-Modal-CelebA-HQ test (5,000)FID: 35.94 -> 31.57Improved
use group sampling instead of random sampling at Na=1 (ablation)ManiCLIP · Multi-Modal-CelebA-HQ test (5,000)FID: 35.50 -> 34.01Improved
use group sampling instead of random sampling at Na=5 (ablation)ManiCLIP · Multi-Modal-CelebA-HQ test (5,000)FID: 37.80 -> 36.26Improved
increase group-sampled attribute number from 3 to 5 (ablation)ManiCLIP · Multi-Modal-CelebA-HQ test (5,000)FID: 31.57 -> 36.26Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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