Research map / Architectures and efficiency / CNN design
Designing Energy-Efficient Convolutional Neural Networks Using Energy-Aware Pruning
Tien-Ju Yang, Yu-Hsin Chen, Vivienne Sze
Check 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 |
|---|---|---|---|
| Apply energy-aware pruning | AlexNet · ImageNet ILSVRC 2014 validation | Normalized energy per image: 3.97 -> 1.06 | Improved |
| Apply energy-aware pruning instead of magnitude-based pruning | AlexNet · ImageNet ILSVRC 2014 validation | Normalized energy per image: 1.85 -> 1.06 | Improved |
| Apply energy-aware pruning | GoogLeNet · ImageNet ILSVRC 2014 validation | Normalized energy per image: 7.63 -> 4.76 | Improved |
| Apply energy-aware pruning | SqueezeNet · ImageNet ILSVRC 2014 validation | Normalized energy per image: 5.28 -> 3.99 | Improved |
| Apply energy-aware pruning instead of magnitude-based pruning | SqueezeNet · ImageNet ILSVRC 2014 validation | Normalized energy per image: 4.61 -> 3.99 | Improved |
| Reduce the number of target classes | AlexNet · ImageNet ILSVRC 2014 validation, reduced-class models | Normalized energy | Mixed |
| Use model size as a proxy for energy consumption | CNN architecture comparison · ImageNet ILSVRC 2014 | Normalized energy | Hurt |
| Use number of MACs as a proxy for energy consumption | CNN architecture comparison · ImageNet ILSVRC 2014 | Normalized energy | Hurt |
Closest papers by meaning
- Towards Energy Efficient Spiking Neural Networks: An Unstructured Pruning Framework (ICLR 2024 · similarity 0.88)
- E2-Train: Training State-of-the-art CNNs with Over 80% Energy Savings (NeurIPS 2019 · similarity 0.88)
- The Hidden Joules: Evaluating the Energy Consumption of Vision Backbones for Progress Towards More Efficient Model Inference (ICML 2025 · similarity 0.87)
- ThiNet: Pruning CNN Filters for a Thinner Net (TPAMI 2018 · similarity 0.87)
- Pruning Filters for Efficient ConvNets (ICLR 2017 · similarity 0.87)
- Faster CNNs with Direct Sparse Convolutions and Guided Pruning (ICLR 2017 · 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.
