Mixed Autoencoder for Self-Supervised Visual Representation Learning

Author:

Chen Kai1,Liu Zhili1,Hong Lanqing2,Xu Hang2,Li Zhenguo2,Yeung Dit-Yan1

Affiliation:

1. Hong Kong University of Science and Technology

2. Huawei Noah's Ark Lab

Publisher

IEEE

Reference49 articles.

1. Unsupervised Visual Representation Learning by Context Prediction

2. Bert: Pre-training of deep bidirectional transformers for language understanding;devlin;ArXiv Preprint,2018

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

4. Peco: Perceptual codebook for bert pre-training of vision transformers;dong;ArXiv Preprint,2021

5. ImageNet: A large-scale hierarchical image database

Cited by 5 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. Beyond traditional visual object tracking: a survey;International Journal of Machine Learning and Cybernetics;2024-08-26

2. A deep learning-based compression and classification technique for whole slide histopathology images;International Journal of Information Technology;2024-06-09

3. RETRACTED: Fusion of Mask RCNN and multi-augmentation for rice recognition;Journal of Intelligent & Fuzzy Systems;2024-04-18

4. IENet: inheritance enhancement network for video salient object detection;Multimedia Tools and Applications;2024-02-03

5. CL-MAE: Curriculum-Learned Masked Autoencoders;2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV);2024-01-03

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