paper-with-me

Papers

Speeding up Convolutional Neural Networks with Low Rank Expansions

2014-05-15 · Max Jaderberg, Andrea Vedaldi, Andrew Zisserman

The focus of this paper is speeding up the evaluation of convolutional neural networks. While delivering impressive results across a range of computer vision and machine learning tasks, these networks are computationally demanding, limiting their deployability. Convolutional layers generally consume the bulk of the processing time, and so in this work we present two simple schemes for drastically speeding up these layers. This is achieved by exploiting cross-channel or filter redundancy to construct a low rank basis of filters that are rank-1 in the spatial domain. Our methods are architecture agnostic, and can be easily applied to existing CPU and GPU convolutional frameworks for tuneable speedup performance. We demonstrate this with a real world network designed for scene text character recognition, showing a possible 2.5x speedup with no loss in accuracy, and 4.5x speedup with less than 1% drop in accuracy, still achieving state-of-the-art on standard benchmarks.

📄 PDF Abstract BibTeX arXiv:1405.3866

Code (0)

등록된 구현이 없습니다.

Tasks

CPUGPUModel Compression

Similar Papers 제목 키워드 기반

Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition

2014-12-19 · Vadim Lebedev, Yaroslav Ganin, Maksim Rakhuba, Ivan Oseledets 외

We propose a simple two-step approach for speeding up convolution layers within large convolutional neural networks based on tensor decomposition and discriminative fine-tuning. Given a layer, we use non-linear least squ…

CPUGeneral ClassificationTensor Decomposition

Convolutional neural networks with low-rank regularization

2015-11-19 · Cheng Tai, Tong Xiao, Yi Zhang, Xiaogang Wang 외

Large CNNs have delivered impressive performance in various computer vision applications. But the storage and computation requirements make it problematic for deploying these models on mobile devices. Recently, tensor de…

Data AugmentationTensor Decomposition

Dynamic Image Networks for Action Recognition

2016-06-01 · CVPR 2016 6 · Hakan Bilen, Basura Fernando, Efstratios Gavves, Andrea Vedaldi 외

We introduce the concept of dynamic image, a novel compact representation of videos useful for video analysis especially when convolutional neural networks (CNNs) are used. The dynamic image is based on the rank pooling …

Action RecognitionTemporal Action Localization

Speeding up convolutional networks pruning with coarse ranking

2019-02-18 · Zi Wang, Chengcheng Li, Dali Wang, Xiangyang Wang 외

Channel-based pruning has achieved significant successes in accelerating deep convolutional neural network, whose pipeline is an iterative three-step procedure: ranking, pruning and fine-tuning. However, this iterative p…

Gaussian Process Regression under Computational and Epistemic Misspecification

2023-12-14 · Daniel Sanz-Alonso, Ruiyi Yang

Gaussian process regression is a classical kernel method for function estimation and data interpolation. In large data applications, computational costs can be reduced using low-rank or sparse approximations of the kerne…

regression