Discrete Cosin TransFormer: Image Modeling From Frequency Domain

Author:

Li Xinyu1,Zhang Yanyi2,Yuan Jianbo1,Lu Hanlin1,Zhu Yibo1

Affiliation:

1. ByteDance

2. Rutgers University

Publisher

IEEE

Reference61 articles.

1. Band-limited training and inference for convolutional neural networks;dziedzic;International Conference on Machine Learning,2019

2. Aggregated Residual Transformations for Deep Neural Networks

3. An image is worth 16x16 words: Transformers for image recognition at scale;dosovitskiy,2020

4. FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search

5. Image quality measures and their performance

Cited by 7 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Multi-scale frequency domain learning for texture classification;International Journal of Machine Learning and Cybernetics;2024-08-14

2. DBFFT: Adversarial-robust dual-branch frequency domain feature fusion in vision transformers;Information Fusion;2024-08

3. Child FER: Domain-Agnostic Facial Expression Recognition in Children Using a Secondary Image Diffusion Model;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

4. Frequency-Based Optimal Style Mix for Domain Generalization in Semantic Segmentation of Remote Sensing Images;IEEE Transactions on Geoscience and Remote Sensing;2024

5. DCT-SwinGAN: Leveraging DCT and Swin Transformer for Face Synthesis from Sketch and Thermal Domains;Communications in Computer and Information Science;2024

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3