SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy

Convolutional Neural Networks (CNNs) have achieved remarkable performance in various computer vision tasks but this comes at the cost of tremendous computational resources, partly due to convolutional layers extracting redundant features. Recent works either compress well-trained large-scale models...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 6153 - 6162
Hlavní autoři: Li, Jiafeng, Wen, Ying, He, Lianghua
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2023
Témata:
Computational efficiency
Computational modeling
Computer vision
Computer vision for social good
Convolution
Convolutional neural networks
Feature extraction
Redundancy
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Convolutional Neural Networks (CNNs) have achieved remarkable performance in various computer vision tasks but this comes at the cost of tremendous computational resources, partly due to convolutional layers extracting redundant features. Recent works either compress well-trained large-scale models or explore well-designed lightweight models. In this paper, we make an attempt to exploit spatial and channel redundancy among features for CNN compression and propose an efficient convolution module, called SCConv (Spatial and Channel reconstruction Convolution), to decrease redundant computing and facilitate representative feature learning. The proposed SCConv consists of two units: spatial reconstruction unit (SRU) and channel reconstruction unit (CRU). SRU utilizes a separate-and-reconstruct method to suppress the spatial redundancy while CRU uses a split-transform-and-fuse strategy to diminish the channel redundancy. In addition, SCConv is a plug-and-play architectural unit that can be used to replace standard convolution in various convolutional neural networks directly. Experimental results show that SCConv-embedded models are able to achieve better performance by reducing redundant features with significantly lower complexity and computational costs.
ISSN:1063-6919
DOI:10.1109/CVPR52729.2023.00596