AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Discrete Contrastive Diffusion for Cross-Modal Music and Image Generation

Ye Zhu, Yu Wu, Kyle Olszewski, Jian Ren, Sergey Tulyakov, Yan Yan

ICLR 2023 · Image generation › Autoregressive and latent generation · approach: High-resolution diffusion synthesis · 9 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 step-wise parallel diffusion with intra-sample negatives (ablation)Vanilla dance-to-music diffusion · AIST++Beats Coverage: 89.0$\pm$1.1 -> 93.9$\pm$}1.2Improved
Add step-wise parallel diffusion with intra-sample negatives (ablation)Vanilla dance-to-music diffusion · AIST++Beats Hit: 83.8$\pm$1.5 -> 90.7$\pm$1.5Improved
Add sample-wise auxiliary diffusion with inter-sample negatives (ablation)Vanilla dance-to-music diffusion · AIST++Genre Accuracy: 25.3$\pm$0.8 -> 27.2$\pm$0.5Improved
Add CDCD contrastive training (ablation)Dance-to-music diffusion · AIST++Quality MOS: 3.6 -> 3.6No clear effect
Add step-wise parallel diffusion with intra-sample negatives (ablation)Vanilla dance-to-music diffusion · TikTok Dance-MusicBeats Hit: 81.4 -> 86.3Improved
Use inter-sample negatives instead of intra-sample negatives in step-wise diffusion (ablation)Step-wise parallel diffusion · AIST++Beats Coverage: 93.9$\pm$}1.2 -> 92.4$\pm$1.0Hurt
Use intra-sample negatives instead of inter-sample negatives in sample-wise diffusion (ablation)Sample-wise auxiliary diffusion · AIST++Genre Accuracy: 27.2$\pm$0.5 -> 26.0$\pm$0.8Hurt
Add sample-wise auxiliary diffusion with inter-sample negatives (ablation)VQ-D text-to-image diffusion · CUB-200FID: 14.61 -> 12.61Improved
Add sample-wise auxiliary diffusion with inter-sample negatives (ablation)VQ-D text-to-image diffusion · MSCOCOCLIPScore: 65.53 -> 66.79Improved
Use sample-wise auxiliary diffusion with inter-sample negatives rather than step-wise parallel diffusion with intra-sample negatives (ablation)CDCD text-to-image diffusion · CUB-200FID: 12.73 -> 12.61Improved
Use sample-wise auxiliary diffusion with inter-sample negatives rather than step-wise parallel diffusion with intra-sample negatives (ablation)CDCD text-to-image diffusion · MSCOCOFID: 32.25 -> 28.76Improved
Apply CDCD contrastive diffusionVanilla diffusion · Dance-to-music AIST++Diffusion steps to convergence: 120 -> 80; ~35%Improved

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