Research map / Image generation / Fast diffusion sampling
Studying Classifier(-Free) Guidance from a Classifier-Centric Perspective
Xiaoming Zhao, Alex Schwing
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add flow-matching postprocessing to CFG samples | EDM with CFG · CIFAR-10 (CFG scale 2.25) | conditional FID: 8.016 -> 5.821 | Improved |
| add flow-matching postprocessing to CFG samples | EDM with CFG · CIFAR-10 (CFG scale 2.50) | conditional FID: 9.402 -> 5.936 | Improved |
| add flow-matching postprocessing to CFG samples | EDM with CFG · CIFAR-10 (CFG scale 2.75) | conditional FID: 10.75 -> 6.176 | Improved |
| sample random target from top-20 nearest neighbors instead of the single nearest neighbor in postprocessing (ablation) | flow-matching postprocessing · 2D Fractal, class 0, w=1 | avg NN distance (x10^-5): 3.11 -> 1.57 | Improved |
| increase guidance scale (ablation) | classifier guidance and CFG · 1D and 2D fractal synthetic data | distance of trajectories from decision boundary | Improved |
| add flow-matching postprocessing | classifier guidance and CFG · MNIST | generation fidelity (qualitative) | Improved |
| add flow-matching postprocessing with several feature-space distance metrics (DINOv2, VAE, classifier) | EDM2 · ImageNet 512 | generation quality | No clear effect |
Closest papers by meaning
- Provably Reliable Classifier Guidance via Cross-Entropy Control (NeurIPS 2026 · similarity 0.91)
- Elucidating the design space of classifier-guided diffusion generation (ICLR 2024 · similarity 0.90)
- Rectified Diffusion Guidance for Conditional Generation (CVPR 2025 · similarity 0.90)
- No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models (ICLR 2025 · similarity 0.90)
- TFG: Unified Training-Free Guidance for Diffusion Models (NeurIPS 2024 · similarity 0.90)
- Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Models (AAAI 2025 · similarity 0.90)
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.
