Research map / Architectures and efficiency / CNN design
Exploring Unexplored Tensor Network Decompositions for Convolutional Neural Networks
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 |
|---|---|---|---|
| Search over Einconv layers with nonlinear activations, multiple convolutions, and varied inner dimensions | LeNet-5 · Fashion-MNIST | test accuracy: ~ 0.91 -> ~ 0.92 | Helped |
| Search over Einconv layer structures | ResNet-50 · CIFAR-10 | accuracy-parameter tradeoff | Helped |
Closest papers by meaning
- Distribution-Aware Tensor Decomposition for Compression of Convolutional Neural Networks (NeurIPS 2025 · similarity 0.91)
- Convolutions and More as Einsum: A Tensor Network Perspective with Advances for Second-Order Methods (NeurIPS 2024 · similarity 0.90)
- Towards Efficient Tensor Decomposition-Based DNN Model Compression With Optimization Framework (CVPR 2021 · similarity 0.90)
- T-Net: Parametrizing Fully Convolutional Nets With a Single High-Order Tensor (CVPR 2019 · similarity 0.89)
- SVDinsTN: A Tensor Network Paradigm for Efficient Structure Search from Regularized Modeling Perspective (CVPR 2024 · similarity 0.87)
- Coarse-To-Fine Tensor Trains for Compact Visual Representations (ICML 2024 · similarity 0.87)
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.