文章目录
- Wasserstein gan
- Transformer
- VIT
- Resvit Residual vision transformers for multi-modal medical image synthesis(TMI2022)
- TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
- Masked Autoencoders Are Scalable Vision LearnersMasked Autoencoders Are Scalable Vision Learners
- BraTS2020数据集
- Swin-Transformer网络结构详解
- Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation
- 域适应(ADDA)
Wasserstein gan
GAN有着诸多问题:模式崩溃,难以收敛等等
https://zhuanlan.zhihu.com/p/25071913
Transformer
图解Transformer(完整版)
https://blog.csdn.net/longxinchen_ml/article/details/86533005
自注意力机制(self-attention)
https://blog.csdn.net/m0_63520910/article/details/124100836
Transformer详解之Embedding、Positional Encoding层(面向初学者)
https://blog.csdn.net/qq_41018669/article/details/120341783
Positional Encoding的原理和计算
https://blog.csdn.net/weixin_44012382/article/details/113059423
Cross-Attention
https://blog.csdn.net/m0_63097763/article/details/132293568
通道注意力和空间注意力
https://blog.csdn.net/weixin_46239293/article/details/119739759
https://zhuanlan.zhihu.com/p/624787123
VIT
ViT 论文逐段精读——B站up:跟李沐学AI讲解笔记
主要是将图片变为patch,赋予各种信息,然后当作序列信息交给tranformer处理。
https://zhuanlan.zhihu.com/p/422144659
轻松理解ViT(Vision Transformer)原理及源码
https://zhuanlan.zhihu.com/p/640013974
Resvit Residual vision transformers for multi-modal medical image synthesis(TMI2022)
https://zhuanlan.zhihu.com/p/528184431
TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
https://blog.csdn.net/Acmer_future_victor/article/details/125855664
https://zhuanlan.zhihu.com/p/391886528
Masked Autoencoders Are Scalable Vision LearnersMasked Autoencoders Are Scalable Vision Learners
https://zhuanlan.zhihu.com/p/439554945
BraTS2020数据集
https://blog.csdn.net/weixin_43953722/article/details/107521440 BraTS数据集处理详解(附代码详解)
https://blog.csdn.net/m0_46223009/article/details/128126000 Python第三方库之nibabel
https://blog.csdn.net/huangdianye/article/details/131692451 医学图像处理——读取和解读NII文件
https://blog.csdn.net/qq_44289607/article/details/123032453 nii数据的各种处理详解
Swin-Transformer网络结构详解
https://blog.csdn.net/weixin_54546190/article/details/124422937 代码讲解
Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation
https://blog.csdn.net/weixin_49627776/article/details/117305352 [深度学习论文笔记]Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation
https://zhuanlan.zhihu.com/p/384514268?ivk_sa=1024320u 代码讲解
https://blog.csdn.net/weixin_43788575/article/details/121074755 Swin-Unet:Swin Transformer在医学分割上的首次尝试
域适应(ADDA)
https://zhuanlan.zhihu.com/p/421214903
https://blog.csdn.net/dou3516/article/details/127149237
https://blog.csdn.net/qq_16488989/article/details/109645773
拉普拉斯金字塔和高斯金字塔: