Text

Learning Versatile Convolution Filters for Efficient Visual Recognition

This paper introduces versatile filters to construct efficient convolutional neural networks that are widely used in various visual recognition tasks. Considering the demands of efficient deep learning techniques running on cost-effective hardware, a number of methods have been developed to learn compact neural networks. Most of these works aim to slim down filters in different ways, e.g., investigating small, sparse or quantized filters. In contrast, we treat filters from an additive perspective. A series of secondary filters can be derived from a primary filter with the help of binary masks. These secondary filters all inherit in the primary filter without occupying more storage, but once been unfolded in computation they could significantly enhance the capability of the filter by integrating information extracted from different receptive fields. Besides spatial versatile filters, we additionally investigate versatile filters from the channel perspective. Binary masks can be further customized for different primary filters under orthogonal constraints. We conduct theoretical analysis on network complexity and an efficient convolution scheme is introduced. Experimental results on benchmark datasets and neural networks demonstrate that our versatile filters are able to achieve comparable accuracy as that of original filters, but require less memory and computation cost.

Ketersediaan

Informasi Detail

Judul Seri

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE; Vol.44 No.11 Part 1 November 2022

No. Panggil

-

Penerbit

: .,

Deskripsi Fisik

p. 7731-7746

Bahasa

English

ISBN/ISSN

-

Klasifikasi

NONE

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

CNN COMPRESSION
CNN SPEED-UP
VERSATILE FILTERS

Info Detail Spesifik

DOI: 10.1109/TPAMI.2021.3114368

Pernyataan Tanggungjawab

Kai Han, Yunhe Wang, Chang Xu, Chunjing Xu, Enhua Wu, Dacheng Tao

Versi lain/terkait

Lampiran Berkas

Komentar