AI Paper Atlas

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

Unsupervised Stylish Image Description Generation via Domain Layer Norm

Cheng-Kuan Chen, Zhufeng Pan, Ming-Yu Liu, Min Sun

AAAI 2019 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 32 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
use Domain Layer Norm rather than NSTstylish image description generation · Lyricscontent similarity: 0.037 -> 0.083Improved
use Domain Layer Norm rather than NSTstylish image description generation · Romancecontent similarity: 0.088 -> 0.151Improved
use Domain Layer Norm rather than NSTstylish image description generation · Humorcontent similarity: 0.103 -> 0.173Improved
use Domain Layer Norm rather than NSTstylish image description generation · Fairy talecontent similarity: 0.116 -> 0.135Improved
use Domain Layer Norm rather than NSTstylish image description generation · Lyricstransfer accuracy: 100% -> 99.2%Hurt
use Domain Layer Norm rather than NSTstylish image description generation · Humortransfer accuracy: 99.7% -> 70.0%Hurt
replace DLN's LN-LSTM with a simple RNN (ablation)DLN · VG-Para testBLEU-4: 0.080 -> 0.062Hurt
progressively add styles to the model (DLN-Multi)DLN · Lyricscontent similarity: 0.083 -> 0.118Improved
progressively add styles to the model (DLN-Multi)DLN · Romancecontent similarity: 0.151 -> 0.116Hurt
progressively add styles to the model (DLN-Multi)DLN · Fairy talecontent similarity: 0.135 -> 0.120Hurt

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