paper-with-me

Papers

Compacting Binary Neural Networks by Sparse Kernel Selection

2023-03-25 · CVPR 2023 1 · Yikai Wang, Wenbing Huang, Yinpeng Dong, Fuchun Sun, Anbang Yao

Binary Neural Network (BNN) represents convolution weights with 1-bit values, which enhances the efficiency of storage and computation. This paper is motivated by a previously revealed phenomenon that the binary kernels in successful BNNs are nearly power-law distributed: their values are mostly clustered into a small number of codewords. This phenomenon encourages us to compact typical BNNs and obtain further close performance through learning non-repetitive kernels within a binary kernel subspace. Specifically, we regard the binarization process as kernel grouping in terms of a binary codebook, and our task lies in learning to select a smaller subset of codewords from the full codebook. We then leverage the Gumbel-Sinkhorn technique to approximate the codeword selection process, and develop the Permutation Straight-Through Estimator (PSTE) that is able to not only optimize the selection process end-to-end but also maintain the non-repetitive occupancy of selected codewords. Experiments verify that our method reduces both the model size and bit-wise computational costs, and achieves accuracy improvements compared with state-of-the-art BNNs under comparable budgets.

📄 PDF Abstract BibTeX arXiv:2303.14470

Code (0)

등록된 구현이 없습니다.

Tasks

Binarization

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Random Features for Compositional Kernels

2017-03-22 · Amit Daniely, Roy Frostig, Vineet Gupta, Yoram Singer

We describe and analyze a simple random feature scheme (RFS) from prescribed compositional kernels. The compositional kernels we use are inspired by the structure of convolutional neural networks and kernels. The resulti…

Diversity

HOTCAKE: Higher Order Tucker Articulated Kernels for Deeper CNN Compression

2020-02-28 · Rui Lin, Ching-Yun Ko, Zhuolun He, Cong Chen 외

The emerging edge computing has promoted immense interests in compacting a neural network without sacrificing much accuracy. In this regard, low-rank tensor decomposition constitutes a powerful tool to compress convoluti…

Edge-computingTensor Decomposition

Optimized Kernel Entropy Components

2016-03-09 · Emma Izquierdo-Verdiguier, Valero Laparra, Robert Jenssen, Luis Gómez-Chova 외

This work addresses two main issues of the standard Kernel Entropy Component Analysis (KECA) algorithm: the optimization of the kernel decomposition and the optimization of the Gaussian kernel parameter. KECA roughly red…

Density Estimation

KSM: Fast Multiple Task Adaption via Kernel-wise Soft Mask Learning

2020-09-11 · CVPR 2021 1 · Li Yang, Zhezhi He, Junshan Zhang, Deliang Fan

Deep Neural Networks (DNN) could forget the knowledge about earlier tasks when learning new tasks, and this is known as \textit{catastrophic forgetting}. While recent continual learning methods are capable of alleviating…

Continual Learning

Log-Linear-Time Gaussian Processes Using Binary Tree Kernels

2022-10-04 · Michael K. Cohen, Samuel Daulton, Michael A. Osborne

Gaussian processes (GPs) produce good probabilistic models of functions, but most GP kernels require $O((n+m)n^2)$ time, where $n$ is the number of data points and $m$ the number of predictive locations. We present a new…

Gaussian Processesregression