Research map / Image generation / Image restoration
Parameter Manifold Purification
Jiacong Hu, Jinxun Wu, Shengxuming Zhang, Shunyu Liu, Haofei Zhang, Mingli Song, Zunlei Feng
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 local manifold positional information (ablation) | IMAE · parameter reconstruction | accuracy: 69.64 -> 75.32 | Improved |
| use PCD loss instead of MSE (ablation) | IMAE · parameter reconstruction | accuracy: 61.42 -> 75.32 | Improved |
| use PCD loss instead of WP loss (ablation) | IMAE · parameter reconstruction | accuracy: 10.86 -> 75.32 | Improved |
| use PCD loss instead of LWLN loss (ablation) | IMAE · parameter reconstruction | accuracy: 67.25 -> 75.32 | Improved |
| tune intra-cluster weight alpha (ablation) | PCD loss · parameter reconstruction | accuracy: peak at alpha = 3 | Mixed |
| increase inter-cluster weight beta (ablation) | PCD loss · parameter reconstruction | accuracy: highest at beta = 2 | Hurt |
| apply PMP to long-tailed ViT-B/16 parameters | ViT-B/16 · ImageNet-LT | overall accuracy: 78.0 -> 82.6 | Improved |
| apply PMP to noisy-label ResNet-34 parameters | ResNet-34 · CIFAR-10 (80% symmetric noise) | accuracy: 67.43 -> 94.20 | Improved |
| apply PMP to backdoored PreAct-ResNet-18 | PreAct-ResNet-18 · Tiny-ImageNet BadNets-A2O | attack success rate: 99.96 -> 0.21 | Improved |
Closest papers by meaning
- Fast, Accurate Manifold Denoising by Tunneling Riemannian Optimization (ICML 2025 · similarity 0.86)
- Consistency Purification: Effective and Efficient Diffusion Purification towards Certified Robustness (NeurIPS 2024 · similarity 0.86)
- Curvature Enhanced Data Augmentation for Regression (ICML 2025 · similarity 0.84)
- Diffusion Models Encode the Intrinsic Dimension of Data Manifolds (ICML 2024 · similarity 0.84)
- MCNC: Manifold-Constrained Reparameterization for Neural Compression (ICLR 2025 · similarity 0.83)
- Adversarial Purification with the Manifold Hypothesis (AAAI 2024 · similarity 0.83)
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.
