AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

CoStoDet-DDPM: Collaborative Training of Stochastic and Deterministic Models Improves Surgical Workflow Anticipation and Recognition

Kaixiang Yang, Xin Li, Qiang Li, Zhiwei Wang

ICCV 2025 · Image generation › Fast diffusion sampling · approach: Diffusion models as perception tools · 1 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 DDPM branch co-training (ablation)CoStoDet-DDPM · Cholec80 anticipation (tool, h=5min)eMAE: 2.11 -> 1.77Improved
add DDPM branch co-training (ablation)CoStoDet-DDPM · Cholec80 anticipation (phase, h=5min)eMAE: 0.99 -> 0.88Improved
add task branch to DDPM (co-training) (ablation)CoStoDet-DDPM · Cholec80 anticipation (tool, h=5min)eMAE: 2.03 -> 1.75Improved
add task branch to DDPM (co-training) (ablation)CoStoDet-DDPM · Cholec80 anticipation (phase, h=5min)eMAE: 1.05 -> 0.86Improved
add task branch to DDPM (co-training) (ablation)CoStoDet-DDPM · Cholec80 anticipation (phase, h=5min)outMAE: 0.19 -> 0.23Mixed
add DDPM branch co-trainingBNPitfalls · Cholec80 recognitionJaccard: 79.2 -> 80.8Improved
add DDPM branch co-trainingDACAT · Cholec80 recognitionJaccard: 80.6 -> 81.4Improved
add DDPM branch co-trainingBNPitfalls · AutoLaparo recognitionJaccard: 64.2 -> 64.4No clear effect
add DDPM branch co-trainingDACAT · AutoLaparo recognitionJaccard: 66.9 -> 67.9Improved
add DDPM branch co-trainingDACAT · AutoLaparo recognitionAccuracy: 87.8 -> 87.6No clear effect
add DDPM branch co-trainingDACAT · Cholec80 recognitionPrecision: 89.2 -> 88.4Hurt
replace DDPM denoising with RandomMask label reconstruction co-training (ablation)BNPitfalls · Cholec80 anticipationwMAE/outMAE/eMAEMixed

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