RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations
Recent advances in vision transformers (ViTs) have demonstrated the advantage of global modeling capabilities, prompting widespread integration of large-kernel convolutions for enlarging the effective receptive field (ERF). However, the quadratic scaling of parameter count and computational complexity (FLOPs) with respect to kernel size poses significant efficiency and optimization challenges. This paper introduces RecConv, a recursive decomposition strategy that efficiently constructs multi-frequency representations using small-kernel convolutions. RecConv establishes a linear relationship between parameter growth and decomposing levels which determines the effective kernel size $k\times 2^\ell$ for a base kernel $k$ and $\ell$ levels of decomposition, while maintaining constant FLOPs regardless of the ERF expansion. Specifically, RecConv achieves a parameter expansion of only $\ell+2$ times and a maximum FLOPs increase of $5/3$ times, compared to the exponential growth ($4^\ell$) of standard and depthwise convolutions. RecNeXt-M3 outperforms RepViT-M1.1 by 1.9 $AP^{box}$ on COCO with similar FLOPs. This innovation provides a promising avenue towards designing efficient and compact networks across various modalities. Codes and models can be found at \url{https://github.com/suous/RecNeXt}.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
SR-R$^2$KAC: Improving Single Image Defocus Deblurring
We propose an efficient deep learning method for single image defocus deblurring (SIDD) by further exploring inverse kernel properties. Although the current inverse kernel method, i.e., kernel-sharing parallel atrous con…
DeblurringImage Defocus DeblurringA time-causal and time-recursive analogue of the Gabor transform
This paper presents a time-causal analogue of the Gabor filter, as well as a both time-causal and time-recursive analogue of the Gabor transform, where the proposed time-causal representations obey both temporal scale co…
Deeply-Recursive Convolutional Network for Image Super-Resolution
We propose an image super-resolution method (SR) using a deeply-recursive convolutional network (DRCN). Our network has a very deep recursive layer (up to 16 recursions). Increasing recursion depth can improve performanc…
Image Super-ResolutionSuper-ResolutionStabilizing GANs with Soft Octave Convolutions
Motivated by recently published methods using frequency decompositions of convolutions (e.g. Octave Convolutions), we propose a novel convolution scheme to stabilize the training and reduce the likelihood of a mode colla…
Generalized Deep Image to Image Regression
We present a Deep Convolutional Neural Network architecture which serves as a generic image-to-image regressor that can be trained end-to-end without any further machinery. Our proposed architecture: the Recursively Bran…
ColorizationDenoisingImage-to-Image Regressionregression