Research map / Architectures and efficiency / CNN design
Discrete Model Compression With Resource Constraint for Deep Neural Networks
Check 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 DMC rather than DCP-Adapt | ResNet-56 · CIFAR-10 | accuracy (pruned): 93.81% vs 93.69% | Hurt |
| use DMC rather than DCP | MobileNetV2 · CIFAR-10 | accuracy change after pruning: +0.26% vs +0.22% | Helped |
| use DMC rather than FPGM | ResNet-34 · ImageNet | ∆-Acc Top-1: -0.73% vs -1.29% | Helped |
| use DMC rather than CCP | ResNet-50 · ImageNet | ∆-Acc Top-1: 0.14% | Helped |
| use DMC rather than FPGM | ResNet-101 · ImageNet | ∆-Acc Top-1: +0.03% vs -0.05% | Helped |
| use DMC rather than DCP | MobileNetV2 · ImageNet | ∆-Acc Top-1: 2.38% | Helped |
| use two gates instead of one gate (ablation) | ResNet-50 · ImageNet | Top-1 accuracy: 75.06% -> 75.35% | Helped |
| use two shared gates instead of one gate (ablation) | MobileNetV2 · ImageNet | Top-1 accuracy: 67.73% -> 68.37% | Helped |
Closest papers by meaning
- Towards Compact CNNs via Collaborative Compression (CVPR 2021 · similarity 0.88)
- Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition (NeurIPS 2021 · similarity 0.88)
- Model Preserving Compression for Neural Networks (NeurIPS 2022 · similarity 0.87)
- Automatic Neural Network Compression by Sparsity-Quantization Joint Learning: A Constrained Optimization-Based Approach (CVPR 2020 · similarity 0.87)
- Model compression via distillation and quantization (ICLR 2018 · similarity 0.87)
- Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers (ICLR 2018 · 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.