Research map / Image generation / Fast diffusion sampling
Learning to Learn Weight Generation via Local Consistency Diffusion
Yunchuan Guan, Yu Liu, Ke Zhou, Zhiqi Shen, Jenq-Neng Hwang, Lei Li
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 meta-learning (bi-level optimization) to diffusion weight generation (ablation) | OCD · Mini-ImageNet 5-way 1-shot | accuracy (%): 59.76 -> 62.53 | Improved |
| add meta-learning to diffusion weight generation (ablation) | OCD · Omniglot 5-way 1-shot | accuracy (%): 95.04 -> 96.65 | Improved |
| add local target weights without consistency loss (ablation) | Mv-Di · Mini-ImageNet 5-way 1-shot | accuracy (%): 62.53 -> 49.72 | Hurt |
| add local target weights without consistency loss (ablation) | Mv-Di · Omniglot 5-way 1-shot | accuracy (%): 96.65 -> 94.28 | Hurt |
| add local consistency loss (ablation) | Tw-Di · Mini-ImageNet 5-way 1-shot | accuracy (%): 49.72 -> 64.87 | Improved |
| add local consistency diffusion (ablation) | Mv-Di · Omniglot 5-way 1-shot | accuracy (%): 96.65 -> 97.34 | Improved |
| add SAM and data augmentation in weight preparation (ablation) | Mc-Di · Omniglot 5-way 1-shot | accuracy | Improved |
| use Mc-Di for transfer learning vs D2NWG | Mc-Di · CIFAR-10 | accuracy (%): 60.42 -> 63.57 | Improved |
| use Mc-Di vs D2NWG | Mc-Di · CIFAR-100 | accuracy (%): 51.50 -> 50.69 | Hurt |
| use Mc-Di vs Meta-Baseline | Mc-Di · Omniglot 5-way 1-shot | accuracy (%): 97.75 -> 97.34 | Hurt |
| use Mc-Di vs D2NWG | Mc-Di · Tiered-ImageNet 5-way 5-shot | accuracy (%): 85.05 -> 88.58 | Improved |
| use Mc-Di vs OCD on DomainNet | Mc-Di · DomainNet 5-way 1-shot | accuracy (%): 64.58 -> 69.05 | Improved |
Closest papers by meaning
- Diffusion-based Neural Network Weights Generation (ICLR 2025 · similarity 0.88)
- Weight Diffusion for Future: Learn to Generalize in Non-Stationary Environments (NeurIPS 2024 · similarity 0.87)
- Transfer Learning for Diffusion Models (NeurIPS 2024 · similarity 0.85)
- Gradient Guidance for Diffusion Models: An Optimization Perspective (NeurIPS 2024 · similarity 0.85)
- TFG: Unified Training-Free Guidance for Diffusion Models (NeurIPS 2024 · similarity 0.85)
- The Emergence of Reproducibility and Consistency in Diffusion Models (ICML 2024 · similarity 0.85)
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.
