SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy

• Published in: Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 6153 - 6162
• Main Authors: Li, Jiafeng, Wen, Ying, He, Lianghua
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2023
• Subjects: Computational efficiency; Computational modeling; Computer vision; Computer vision for social good; Convolution; Convolutional neural networks; Feature extraction; Redundancy
• ISSN: 1063-6919
• DOI: 10.1109/CVPR52729.2023.00596

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.