AI Paper Atlas

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

Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing

Kai Wang, Fei Yang, Shiqi Yang, Muhammad Atif Butt, Joost van de Weijer

NeurIPS 2023 · Image generation › Text-to-image diffusion · approach: Text-driven synthesis and semantic guidance · 14 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
Replace NTI token conditioning with per-timestamp dynamic noun tokens and leakage-repair lossesP2P image editing with Stable Diffusion v1.4 · Cat → leopard; dog → tigerCLIP-Score: 31.50% -> 32.23%Improved
Replace NTI token conditioning with per-timestamp dynamic noun tokens and leakage-repair lossesP2P image editing with Stable Diffusion v1.4 · Cat → leopard; dog → tigerStructure Dist: 0.0800 -> 0.0312Improved
Replace NTI token conditioning with per-timestamp dynamic noun tokens and leakage-repair lossesP2P image editing with Stable Diffusion v1.4 · Book → box; clock → sunflowerCLIP-Score: 12.91% -> 14.29%Improved
Replace NTI token conditioning with per-timestamp dynamic noun tokens and leakage-repair lossesP2P image editing with Stable Diffusion v1.4 · Book → box; clock → sunflowerStructure Dist: 0.0191 -> 0.0163Improved
Replace NTI token conditioning with per-timestamp dynamic noun tokens and leakage-repair lossesP2P image editing with Stable Diffusion v1.4 · Multi-object image translationsUser Study preference: 12.8% -> 87.2%Improved
Use the disjoint object attention loss alone (ablation)Dynamic Prompt Learning · MO-Set validation localizationIoUNo clear effect
Use the background leakage loss alone (ablation)Dynamic Prompt Learning · MO-Set validation localizationIoUNo clear effect
Add the attention balancing loss (ablation)Dynamic Prompt Learning · MO-Set validation localizationIoUImproved
Add the disjoint object and background leakage losses alongside attention balancing (ablation)Dynamic Prompt Learning · MO-Set validation localizationIoUImproved
Optimize noun tokens separately at each timestamp rather than using a single token embedding across timestamps (ablation)Dynamic Prompt Learning · Cross-attention map qualityCross-attention qualityImproved

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