Research map / Architectures and efficiency / Quantization
Performance Guaranteed Network Acceleration via High-Order Residual Quantization
Zefan Li, Bingbing Ni, Wenjun Zhang, Xiaokang Yang, Wen Gao
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 order-two residual quantization of inputs instead of order-one (XNOR) | MLP binary network · MNIST | test error: 1.96% -> 1.25% | Improved |
| use order-two residual quantization of inputs instead of order-one (XNOR) | MLP binary network · MNIST | accuracy: HORQ-Net outperforms XNOR-Net by 0.71% | Improved |
| use order-two residual quantization of inputs instead of order-one (XNOR) | shallow CNN · CIFAR-10 | accuracy drop vs float baseline: ~5% drop -> within 2% drop | Improved |
| use order-two residual quantization instead of order-one | MNIST MLP · MNIST | convergence speed | Improved |
| increase quantization order from one to two (ablation) | HORQ · Speedup ratio (theoretical) | speedup: 58x -> 30x | Hurt |
| increase quantization order from two to three (ablation) | HORQ · Speedup ratio (theoretical) | speedup: 30x -> 20x | Hurt |
| increase quantization order from three to four (ablation) | HORQ · Speedup ratio (theoretical) | speedup: 20x -> 15x | Hurt |
| HORQ with binary input and weight versus BN, BC (float input) | MLP · MNIST | test error: 0.96% -> 1.25% | Hurt |
Closest papers by meaning
- Understanding Neural Network Binarization with Forward and Backward Proximal Quantizers (NeurIPS 2023 · similarity 0.87)
- Flexible Residual Binarization for Image Super-Resolution (ICML 2024 · similarity 0.85)
- Bi-ViT: Pushing the Limit of Vision Transformer Quantization (AAAI 2024 · similarity 0.85)
- Binary Quadratic Quantization: Beyond First-Order Quantization for Real-Valued Matrix Compression (NeurIPS 2025 · similarity 0.84)
- Binarized Diffusion Model for Image Super-Resolution (NeurIPS 2024 · similarity 0.84)
- BiDM: Pushing the Limit of Quantization for Diffusion Models (NeurIPS 2024 · similarity 0.84)
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.
