.png){kind=icon}
.png){kind=icon}
Return
Speeded-up Convolution Neural Network for classification tasks using multiscale 2-dimensional decomposition
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2020.05.068.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In this paper, we propose a strategy for network simplification and acceleration. First, we propose to generate a suitable resized image using multiscale patching in the first convolutional layer, which can then be used for the rest of the network. We use p convolutional filters that operate on patches of size m x n, and we first select all the possible non-superposed m x n patches from the available images. If the number of such patches is not sufficient, the remaining ones are collected using scales a x b or c x d such that ab = cd = mn or a = 2 m or b = 2n. Patches generated from the former condition are directly extracted from the images, while the downsampled results are used in the latter case. We also introduce a 2-dimensional decomposition for patch compression, by stacking all the available image patches along the columns and applying a 2D PCA decomposition. Finally, a layer weight decomposition technique followed by module-based finetuning is adopted, for a new fast module-based CNN model. Extensive evaluations using public data sets like MNIST, Pascal VOC, and WebCASIA, and with different state-of-the art CNN architectures like Open-Face, VGG and DarkNet verify that our proposed model is able to accelerate the training process and even to provide higher classification accuracies for small-sized datasets. We obtain 8% increase in Top-1 and Top-5 recognition rates, and 5% increase in F1 score over general interpolation-based resizing. (C) 2020 Elsevier B.V. All rights reserved.
Keywords:
Image classification
Modular finetuning
Multiscale compression
Weight decomposition
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.