AI Paper Atlas

Research map / Image generation / GANs

GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesis

Ming Tao, Bing-Kun Bao, Hao Tang, Changsheng Xu

CVPR 2023 · Image generation › GANs · approach: Large-scale GAN latent analysis · 164 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
Integrate CLIP-based discriminator and CLIP-empowered generator rather than using CLIP contrastive loss aloneText-to-image GAN · COCO test zero-shotZS-FID: 26.94 -> 16.12Improved
Add CLIP-based discriminator with CLIP-FE (ablation)One-stage text-to-image GAN · COCO testFID: 17.31 -> 7.92Improved
Add CLIP-based discriminator with CLIP-FE (ablation)One-stage text-to-image GAN · COCO testCLIPSIM: 0.2996 -> 0.3221Improved
Replace CLIP-FE with CCM&CSM (ablation)CLIP-based discriminator · COCO testFID: 7.92 -> 10.77Hurt
Add Bridge-FP to the CLIP-based generator (ablation)GALIP without Prompt Predictor · COCO testFID: 7.92 -> 6.52Improved
Add Bridge-FP to the CLIP-based generator (ablation)GALIP without Prompt Predictor · COCO testCLIPSIM: 0.3221 -> 0.3301Improved
Add Prompt Predictor (ablation)GALIP with Bridge-FP · COCO testFID: 6.52 -> 5.85Improved
Add Prompt Predictor (ablation)GALIP with Bridge-FP · COCO testCLIPSIM: 0.3301 -> 0.3338Improved
Use CCM&CSM instead of CLIP-FE (ablation)CLIP-based discriminator · COCO testFID: 7.92 -> 10.77Hurt
Use CLIP-FE features from layers 2, 5, and 9 (ablation)GALIP discriminator · COCO testFID: 6.70 -> 5.85Improved
Add CLIP-FE feature from layer 8 (ablation)GALIP discriminator using layers 2, 5, and 9 · COCO testFID: 5.85 -> 6.01Hurt
Use layer 12 instead of layer 9 as the third CLIP-FE feature (ablation)GALIP discriminator · COCO testFID: 5.85 -> 6.61Hurt

Later papers that compared with this method

1 later accepted paper reports GALIP as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

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