CSpace

浏览/检索结果: 共2条,第1-2条 帮助

已选(0)清除 条数/页:   排序方式:
Long-Tailed Visual Recognition via Improved Cross-Window Self-Attention and TrivialAugment 期刊论文
IEEE ACCESS, 2023, 卷号: 11, 页码: 49601-49610
作者:  Song, Ying;  Li, Mengxing;  Wang, Bo
收藏  |  浏览/下载:14/0  |  提交时间:2023/12/04
Convolutional neural networks  Continuous wavelet transforms  Data models  Training  Computer vision  Transformers  Transfer learning  Long-tailed recognition  self-attention  vision transformer  CNN  TrivialAugment  
RingMo: A Remote Sensing Foundation Model With Masked Image Modeling 期刊论文
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 卷号: 61, 页码: 22
作者:  Sun, Xian;  Wang, Peijin;  Lu, Wanxuan;  Zhu, Zicong;  Lu, Xiaonan;  He, Qibin;  Li, Junxi;  Rong, Xuee;  Yang, Zhujun;  Chang, Hao;  He, Qinglin;  Yang, Guang;  Wang, Ruiping;  Lu, Jiwen;  Fu, Kun
收藏  |  浏览/下载:33/0  |  提交时间:2023/12/04
Foundation model  masked image modeling (MIM)  pretraining  remote sensing (RS)  self-supervised  Vision Transformer (ViT)