Research map / 3D vision / 3D generation
Hilbert Distillation for Cross-Dimensionality Networks
Dian Qin, Haishuai Wang, Zhe Liu, HONGJIA XU, Sheng Zhou, Jiajun Bu
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 |
|---|---|---|---|
| Use Hilbert-curve feature distillation instead of the strongest listed baseline | ResNet-50 student distilled from 3DResNet-50 · ActivityNet | Top-1 accuracy: 62.88 ± 0.36 -> 63.55 ± 0.28 | Improved |
| Use variable-length Hilbert distillation instead of Hilbert distillation | ResNet-50 student distilled from 3DResNet-50 · ActivityNet | Top-1 accuracy: 63.55 ± 0.28 -> 63.71 ± 0.63 | Improved |
| Use Hilbert-curve feature distillation instead of the strongest listed baseline | VGG16 student distilled from 3DResNet-50 · ActivityNet | Top-1 accuracy: 62.27 ± 0.51 -> 63.46 ± 0.49 | Improved |
| Use variable-length Hilbert distillation instead of Hilbert distillation | VGG16 student distilled from 3DResNet-50 · ActivityNet | Top-1 accuracy: 63.46 ± 0.49 -> 64.02 ± 0.85 | Improved |
| Use Hilbert-curve feature distillation instead of the strongest listed baseline | ResNet-50 student distilled from 3DResNet-50 · Large-COVID-19 | Top-1 accuracy: 83.69 ± 0.32 -> 85.05 ± 0.58 | Improved |
| Use variable-length Hilbert distillation instead of Hilbert distillation | ResNet-50 student distilled from 3DResNet-50 · Large-COVID-19 | Top-1 accuracy: 85.05 ± 0.58 -> 85.55 ± 0.72 | Improved |
| Use Hilbert-curve feature distillation instead of the strongest listed baseline | VGG16 student distilled from 3DResNet-50 · Large-COVID-19 | Top-1 accuracy: 82.85 ± 0.46 -> 84.63 ± 0.38 | Improved |
| Use variable-length Hilbert distillation instead of Hilbert distillation | VGG16 student distilled from 3DResNet-50 · Large-COVID-19 | Top-1 accuracy: 84.63 ± 0.38 -> 85.37 ± 0.86 | Improved |
| Use Hilbert-curve feature distillation instead of the strongest listed baseline | ResNet-50 student distilled from 3DResNet-50 · Kinetics-400 | Top-1 accuracy: 69.59 ± 1.02 -> 70.28 ± 0.36 | Improved |
| Use variable-length Hilbert distillation instead of Hilbert distillation | ResNet-50 student distilled from 3DResNet-50 · Kinetics-400 | Top-1 accuracy: 70.28 ± 0.36 -> 70.91 ± 0.85 | Improved |
| Use Hilbert-curve feature distillation instead of the strongest listed baseline | VGG16 student distilled from 3DResNet-50 · Kinetics-400 | Top-1 accuracy: 68.48 ± 0.59 -> 69.82 ± 0.42 | Improved |
| Use variable-length Hilbert distillation instead of Hilbert distillation | VGG16 student distilled from 3DResNet-50 · Kinetics-400 | Top-1 accuracy: 69.82 ± 0.42 -> 70.40 ± 0.73 | Improved |
Closest papers by meaning
- D^4: Dataset Distillation via Disentangled Diffusion Model (CVPR 2024 · similarity 0.85)
- Consistent Geometric Deep Learning via Hilbert Bundles and Cellular Sheaves (NeurIPS 2026 · similarity 0.84)
- VkD: Improving Knowledge Distillation using Orthogonal Projections (CVPR 2024 · similarity 0.83)
- Hyperbolic Dataset Distillation (NeurIPS 2025 · similarity 0.83)
- Cross-Dimension Affinity Distillation for 3D EM Neuron Segmentation (CVPR 2024 · similarity 0.83)
- Unlocking Dataset Distillation with Diffusion Models (NeurIPS 2025 · similarity 0.82)
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.
