Back to Search Start Over

AFIDAF: Alternating Fourier and Image Domain Adaptive Filters as an Efficient Alternative to Attention in ViTs

Authors :
Zheng, Yunling
Xu, Zeyi
Xue, Fanghui
Yang, Biao
Lyu, Jiancheng
Zhang, Shuai
Qi, Yingyong
Xin, Jack
Publication Year :
2024

Abstract

We propose and demonstrate an alternating Fourier and image domain filtering approach for feature extraction as an efficient alternative to build a vision backbone without using the computationally intensive attention. The performance among the lightweight models reaches the state-of-the-art level on ImageNet-1K classification, and improves downstream tasks on object detection and segmentation consistently as well. Our approach also serves as a new tool to compress vision transformers (ViTs).

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2407.12217
Document Type :
Working Paper