paper-with-me

Papers

Performance Guaranteed Network Acceleration via High-Order Residual Quantization

2017-08-29 · ICCV 2017 10 · Zefan Li, Bingbing Ni, Wenjun Zhang, Xiaokang Yang, Wen Gao

Input binarization has shown to be an effective way for network acceleration. However, previous binarization scheme could be regarded as simple pixel-wise thresholding operations (i.e., order-one approximation) and suffers a big accuracy loss. In this paper, we propose a highorder binarization scheme, which achieves more accurate approximation while still possesses the advantage of binary operation. In particular, the proposed scheme recursively performs residual quantization and yields a series of binary input images with decreasing magnitude scales. Accordingly, we propose high-order binary filtering and gradient propagation operations for both forward and backward computations. Theoretical analysis shows approximation error guarantee property of proposed method. Extensive experimental results demonstrate that the proposed scheme yields great recognition accuracy while being accelerated.

📄 PDF Abstract BibTeX arXiv:1708.08687

Code (0)

등록된 구현이 없습니다.

Tasks

BinarizationQuantizationVocal Bursts Intensity Prediction

Similar Papers 제목 키워드 기반

OrderDP: A Theoretically Guaranteed Lossless Dynamic Data Pruning Framework

2026-06-07 · Chenhan Jin, Shengze Xu, Qingsong Wang, Fan Jia 외 arxiv

Data pruning (DP), as an oft-stated strategy to alleviate heavy training burdens, reduces the volume of training samples according to a well-defined pruning method while striving for near-lossless performance. However, e…

Computational Efficiency

Physics-Informed Neural Networks for Satellite State Estimation

2024-03-28 · Jacob Varey, Jessica D. Ruprecht, Michael Tierney, Ryan Sullenberger

The Space Domain Awareness (SDA) community routinely tracks satellites in orbit by fitting an orbital state to observations made by the Space Surveillance Network (SSN). In order to fit such orbits, an accurate model of …

State Estimation

Anderson Acceleration as a Krylov Method with Application to Asymptotic Convergence Analysis

2021-09-29 · Hans De Sterck, Yunhui He, Oliver A. Krzysik

Anderson acceleration (AA) is widely used for accelerating the convergence of nonlinear fixed-point methods $x_{k+1}=q(x_{k})$, $x_k \in \mathbb{R}^n$, but little is known about how to quantify the convergence accelerati…

Multi-Weight Respecification of Scan-specific Learning for Parallel Imaging

2022-04-05 · Hui Tao, Haifeng Wang, Shanshan Wang, Dong Liang 외

Parallel imaging is widely used in magnetic resonance imaging as an acceleration technology. Traditional linear reconstruction methods in parallel imaging often suffer from noise amplification. Recently, a non-linear rob…

Momentum as Residual-Driven Multiplier Correction for Deep Learning Optimization

2026-08-13 · Zhixin Ren, Yau Lyu, Congrong Li, Liping Zhang 외 arxiv

Momentum-based optimizers are widely used in modern deep learning, yet the relations among momentum recursion, update geometry, and acceleration remain only partially understood. We develop an $\textbf{A}$DMM-$\textbf{I}…

Reinforcement Learning