Research map / Architectures and efficiency / CNN design
HODEC: Towards Efficient High-Order DEcomposed Convolutional Neural Networks
Miao Yin, Yang Sui, Wanzhao Yang, Xiao Zang, Yu Gong, Bo Yuan
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 HODEC compression instead of the uncompressed model | ResNet-32 · CIFAR-10 | top-1 accuracy: 92.49 -> 93.05 | Improved |
| Use HODEC compression instead of the uncompressed model | ResNet-56 · CIFAR-10 | top-1 accuracy: 93.04 -> 94.20 | Improved |
| Use HODEC compression instead of the uncompressed model | ResNet-50 · ImageNet | top-1 accuracy: 76.13 -> 76.44 | Improved |
| Use HODEC compression instead of the uncompressed model | ResNet-50 · ImageNet | FLOPs: 63% | Improved |
| Add core convolution between contract-in and contract-out (ablation) | HODEC · CIFAR-10, ResNet-32 trained from scratch | top-1 accuracy: nearly 2% | Improved |
| Use one-stage end-to-end decomposition instead of two-stage decomposition (ablation) | HODEC weight decomposition · ResNet-32 convolution layer | approximation error | Improved |
| Increase decomposition order d (ablation) | HODEC, ResNet-18 layer3.0.conv1 · ImageNet | FLOPs reduction | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SCOP — SCOP: Scientific Control for Reliable Neural Network Pruning (NeurIPS 2020) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Holistic CNN Compression via Low-Rank Decomposition with Knowledge Transfer (TPAMI 2018 · similarity 0.89)
- Towards Compact CNNs via Collaborative Compression (CVPR 2021 · similarity 0.86)
- Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition (NeurIPS 2021 · similarity 0.86)
- Model Preserving Compression for Neural Networks (NeurIPS 2022 · similarity 0.85)
- On Compressing Deep Models by Low Rank and Sparse Decomposition (CVPR 2017 · similarity 0.85)
- C3: High-Performance and Low-Complexity Neural Compression from a Single Image or Video (CVPR 2024 · similarity 0.84)
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.
