AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Deeply Supervised Flow-Based Generative Models

Inkyu Shin, Chenglin Yang, Liang-Chieh Chen

ICCV 2025 · Image generation › Fast diffusion sampling · approach: Rectified flow straightening · 12 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 deep supervision (ablation)SiT-B/2 · ImageNet-256 (B/2, 80 ep, uniform, no CFG)FID: 34.4 -> 33.0Improved
add time-gap between branch time-steps (ablation)SiT-B/2 with deep supervision · ImageNet-256 (B/2, 80 ep, uniform, no CFG)FID: 33.0 -> 31.1Improved
add inter-layer acceleration in VeRA block (ablation)SiT-B/2 with deep supervision and time-gap · ImageNet-256 (B/2, 80 ep, uniform, no CFG)FID: 31.1 -> 29.9Improved
add cross-space attention in VeRA block (ablation)DeepFlow-B/2-2T · ImageNet-256 (B/2, 80 ep, uniform, no CFG)FID: 29.9 -> 28.1Improved
modulate concatenated velocity and acceleration instead of adding modulated acceleration to velocity (ablation)DeepFlow-B/2-2T VeRA block · ImageNet-256 (B/2, 80 ep, uniform, no CFG)FID: 29.3 -> 28.1Improved
deeper ACC_MLP {2048, 4096, 2048, 768} instead of {2048, 768} (ablation)DeepFlow-B/2-2T · ImageNet-256 (B/2, 80 ep, uniform, no CFG)FID: 30.4 -> 28.1Improved
vary maximum time-gap alpha from 0.1 to 0.001 (ablation)DeepFlow-B/2-2T · ImageNet-256 (B/2, 80 ep, uniform, no CFG)FID: 28.9 (0.1), 28.6 (0.05), 28.1 (0.01), 28.3 (0.005), 28.5 (0.001)No clear effect
vary acceleration loss weight lambda from 0.5 to 1.5 (ablation)DeepFlow-B/2-2T · ImageNet-256 (B/2, 80 ep, uniform, no CFG)FID: 27.8 (0.5), 28.1 (1.0), 28.8 (1.5)Mixed
replace SiT-B/2 with DeepFlow-B/2-2T (no SSL, lognormal)SiT-B/2 · ImageNet-256 (B/2, 80 ep, no CFG)FID: 29.7 -> 23.1Improved
add DINOv2 SSL alignment to DeepFlow-B/2-2T (lognormal)DeepFlow-B/2-2T · ImageNet-256 (B/2, 80 ep, no CFG)FID: 23.1 -> 17.2Improved
replace SiT-XL/2 with DeepFlow-XL/2-3T (no SSL, 80 ep)SiT-XL/2 · ImageNet-256 (XL/2, 80 ep, no CFG)FID: 13.8 -> 10.3Improved
apply DINOv2 alignment twice in SiTSiT · ImageNet-256FIDNo clear effect

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