Research map / Learning theory and algorithms / Combinatorial and search optimization
ECC: Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model
Haichuan Yang, Yuhao Zhu, Ji Liu
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 |
|---|---|---|---|
| Use ECC instead of NetAdapt | ERFNet · Cityscapes, GTX 1080 Ti, 1.3843 J | averaged IoU: 0.6361 -> 0.6713 | Improved |
| Use ECC instead of AMC | ERFNet · Cityscapes, GTX 1080 Ti, 1.3843 J | averaged IoU: 0.6340 -> 0.6713 | Improved |
| Use ECC instead of NetAdapt | ERFNet · Cityscapes, Jetson TX2, 0.8542 J | averaged IoU: 0.6567 -> 0.6733 | Improved |
| Use ECC instead of AMC | ERFNet · Cityscapes, Jetson TX2, 0.8542 J | averaged IoU: 0.6344 -> 0.6733 | Improved |
| Add an MLP after the bilinear energy model (ablation) | ECC energy prediction on MobileNet · GTX 1080 Ti | relative test error | No clear effect |
| Add an MLP after the bilinear energy model (ablation) | ECC energy prediction on MobileNet · Jetson TX2 | relative test error | Hurt |
| Use ECC instead of NetAdapt | MobileNet · ImageNet, Jetson TX2, 0.0247 J | top-1 accuracy: 2.6% | Improved |
| Use ECC instead of NetAdapt before fine-tuning | MobileNet · ImageNet, Jetson TX2, 0.037 J | top-1 accuracy: 17.5% | Improved |
Closest papers by meaning
- Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Masking (ICLR 2019 · similarity 0.91)
- "Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach (NeurIPS 2022 · similarity 0.87)
- DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks (ICML 2022 · similarity 0.87)
- HALOC: Hardware-Aware Automatic Low-Rank Compression for Compact Neural Networks (AAAI 2023 · similarity 0.85)
- Resource-Efficient Neural Networks for Embedded Systems (JMLR 2024 · similarity 0.85)
- MEET: Towards Memory-Efficient Temporal Sparse Deep Neural Networks (CVPR 2025 · 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.
