Saved in:
Bibliographic Details
Main Authors: Zheng, Yunling, Xu, Zeyi, Xue, Fanghui, Yang, Biao, Lyu, Jiancheng, Zhang, Shuai, Qi, Yingyong, Xin, Jack
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.12217
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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).