Research map / Architectures and efficiency / CNN design
Channel Gating Neural Networks
Weizhe Hua, Yuan Zhou, Christopher M De Sa, Zhiru Zhang, G. Edward Suh
Read the paperCheck 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 dynamic channel gating | CNN architectures · CIFAR-10 | FLOP reduction: 2.7 - 8.0× | Improved |
| Add channel grouping (ablation) | CGNet-A · ImageNet | top-1 accuracy drop: 1.3 -> 0.4 | Improved |
| Add channel grouping (ablation) | CGNet-A · ImageNet | FLOP reduction: $1.61\times$ -> $1.93\times$ | Improved |
| Add knowledge distillation (ablation) | CGNet-A with channel grouping · ImageNet | top-1 accuracy drop: 0.4 -> -0.5 | Improved |
| Add knowledge distillation (ablation) | CGNet-A with channel grouping · ImageNet | FLOP reduction: $1.93\times$ -> $2.55\times$ | Improved |
| Add knowledge distillation (ablation) | CGNet · CIFAR-10 | accuracy | No clear effect |
| Use activation-wise and channel-wise gates | CGNet · CIFAR-10 | weight accesses: 3.1× and 4.4× | Improved |
| Increase the target threshold T | CGNet with channel-wise gate · CIFAR-10 | weight accesses: T equals 1.5 and 2.0 | Improved |
| Use channel grouping instead of a fixed base-path channel selection (ablation) | CGNet · CIFAR-10 | top-1 accuracy: 0.8% | Improved |
Closest papers by meaning
- Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers (ICLR 2018 · similarity 0.90)
- Soft Masking for Cost-Constrained Channel Pruning (ECCV 2022 · similarity 0.88)
- Dynamic Dual Gating Neural Networks (ICCV 2021 · similarity 0.88)
- BilevelPruning: Unified Dynamic and Static Channel Pruning for Convolutional Neural Networks (CVPR 2024 · similarity 0.86)
- REPrune: Channel Pruning via Kernel Representative Selection (AAAI 2024 · similarity 0.86)
- Rethinking Neural Nonlinearity as Gating (NeurIPS 2026 · similarity 0.86)
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.
