AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Text-Driven Generative Domain Adaptation with Spectral Consistency Regularization

Zhenhuan Liu, Liang Li, Jiayu Xiao, Zheng-Jun Zha, Qingming Huang

ICCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 6 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 spectral consistency regularization to directional-loss adaptationStyleGAN-NADA · Photo->SketchHessian trace: 0.061 -> 0.116Improved
add spectral consistency regularization to directional-loss adaptationStyleGAN-NADA · Photo->SketchPPL: 323.25 -> 463.57Improved
add spectral consistency regularization to directional-loss adaptationStyleGAN-NADA · Human->WerewolfPPL: 302.91 -> 383.19Improved
use SCC, WDC or MS regularization instead of spectral consistencytext-driven GAN adaptation · diversity vs stylizationstylization (qualitative)Hurt
use PPL or CDC regularization instead of spectral consistencytext-driven GAN adaptation · diversityHessian trace / PPL: Photo->Sketch trace 0.028 (PPL reg), 0.062 (CDC) vs 0.116 (Ours)Hurt
apply regularization only to coarse, only to fine, or global granularity instead of adaptive soft mask (ablation)Granularity adaptive regularization · Photo->Edvard Munch (qualitative)diversity and styleImproved
increase lambda_spectral (ablation)Spectral consistency regularization · qualitative samplesdiversityImproved
use CLIP image encoder as metric space instead of VGG, MoCo, ArcFace or pixel space (ablation)Spectral consistency regularization · identity preservation (qualitative)identity of source imageImproved
add spectral consistency regularization versus WDC in user studyOurs vs WDC · user study, attribute consistencypreference (%): 49.8%No 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