AI Paper Atlas

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

ICCV 2017 · Architectures and efficiency › Quantization · approach: Binary neural networks · 110 citations (OpenAlex)

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 changedWhereMeasuredEffect
use order-two residual quantization of inputs instead of order-one (XNOR)MLP binary network · MNISTtest error: 1.96% -> 1.25%Improved
use order-two residual quantization of inputs instead of order-one (XNOR)MLP binary network · MNISTaccuracy: HORQ-Net outperforms XNOR-Net by 0.71%Improved
use order-two residual quantization of inputs instead of order-one (XNOR)shallow CNN · CIFAR-10accuracy drop vs float baseline: ~5% drop -> within 2% dropImproved
use order-two residual quantization instead of order-oneMNIST MLP · MNISTconvergence speedImproved
increase quantization order from one to two (ablation)HORQ · Speedup ratio (theoretical)speedup: 58x -> 30xHurt
increase quantization order from two to three (ablation)HORQ · Speedup ratio (theoretical)speedup: 30x -> 20xHurt
increase quantization order from three to four (ablation)HORQ · Speedup ratio (theoretical)speedup: 20x -> 15xHurt
HORQ with binary input and weight versus BN, BC (float input)MLP · MNISTtest error: 0.96% -> 1.25%Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy