Research map / Architectures and efficiency / CNN design
Lipschitz Continuity Retained Binary Neural Network
Yuzhang Shang, Dan Xu, Bin Duan, Ziliang Zong, Liqiang Nie, Yan Yan
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 |
|---|---|---|---|
| add LCR Lipschitz regularizer (ablation) | IR-Net w/o BiReal · ImageNet ResNet-18 | top-1 accuracy (%): 56.9 -> 58.4 | Improved |
| add LCR regularizer (ablation) | IR-Net with BiReal · ImageNet ResNet-18 | top-1 accuracy (%): 58.1 -> 59.6 | Improved |
| add LCR regularizer (ablation) | ReActNet · ImageNet | top-1 accuracy (%): 69.4 -> 69.8 | Improved |
| add LCR regularizer (ablation) | IR-Net w/o BiReal · CIFAR-10 ResNet-20 | top-1 accuracy (%): 85.5 -> 86.0 | Improved |
| add LCR regularizer (ablation) | IR-Net with BiReal · CIFAR-10 ResNet-20 | top-1 accuracy (%): 86.5 -> 87.2 | Improved |
| increase lambda from 0 to 2^3 (ablation) | LCR-BNN ResNet-18 · CIFAR-10 | top-1 accuracy (%): 85.9 -> 91.8 | Improved |
| increase lambda from 0 to 2^2 (ablation) | LCR-BNN ResNet-20 · CIFAR-10 | top-1 accuracy (%): 83.9 -> 87.2 | Improved |
| raise lambda from 2^2 to 2^3 (ablation) | LCR-BNN ResNet-20 · CIFAR-10 | top-1 accuracy (%): 87.2 -> 86.5 | Hurt |
| add LCR regularizer | IR-Net · ImageNet-C | mCE (%): 89.2 -> 84.9 | Improved |
| add LCR regularizer | RBNN · ImageNet-C | mCE (%): 87.5 -> 84.8 | Improved |
| LCR instead of ProxyBNN (ResNet-18) | LCR-BNN · ImageNet | top-1 accuracy (%): 58.7 -> 59.6 | Improved |
| add LCR regularizer at inference cost | LCR-BNN · ResNet-18 BOPS/FLOPS | BOPS and FLOPS: 1.676 x 10^9 -> 1.676 x 10^9 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- ProxyBNN — ProxyBNN: Learning Binarized Neural Networks via Proxy Matrices (ECCV 2020) · better on 2 of 2 shared results
- XNOR-Net — XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks (ECCV 2016) · 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
- Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz Regularization (NeurIPS 2023 · similarity 0.89)
- ECLipsE: Efficient Compositional Lipschitz Constant Estimation for Deep Neural Networks (NeurIPS 2024 · similarity 0.88)
- Some Fundamental Aspects about Lipschitz Continuity of Neural Networks (ICLR 2024 · similarity 0.88)
- Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Loss (ICML 2025 · similarity 0.88)
- A provable control of sensitivity of neural networks through a direct parameterization of the overall bi-Lipschitzness (NeurIPS 2024 · similarity 0.86)
- Approximation theory for 1-Lipschitz ResNets (NeurIPS 2025 · 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.
