Research map / Architectures and efficiency / CNN design
Convolutional Neural Fabrics
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 dense rather than sparse channel connectivity (ablation) | Convolutional Neural Fabrics · MNIST test | error rate: 0.48 -> 0.33 | Helped |
| Use dense rather than sparse channel connectivity (ablation) | Convolutional Neural Fabrics · CIFAR10 test | error rate: 18.89 -> 7.43 | Helped |
| Use dense rather than sparse channel connectivity (ablation) | Convolutional Neural Fabrics · Part Labels test | superpixel accuracy: 95.58 -> 95.63 | No clear effect |
| Use dense rather than sparse channel connectivity (ablation) | Convolutional Neural Fabrics · Part Labels test | pixel accuracy: 94.60 -> 94.82 | Helped |
| Prune 67% of connections and fine-tune (ablation) | Dense CNF trained on CIFAR10 · CIFAR10 | error rate: 7.4% to 8.1% | Hurt |
Closest papers by meaning
- Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells (CVPR 2019 · similarity 0.85)
- AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures (ICLR 2020 · similarity 0.85)
- OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation (CVPR 2024 · similarity 0.84)
- CT-Net: Channel Tensorization Network for Video Classification (ICLR 2021 · similarity 0.84)
- PICNN: A Pathway towards Interpretable Convolutional Neural Networks (AAAI 2024 · similarity 0.83)
- Receptive Fields As Experts in Convolutional Neural Architectures (ICML 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.