Autoencoder based self-supervised test-time adaptation for medical image analysis

1.作者

主要是 约翰霍普金斯大学和美国国家老龄问题研究所,国家卫生研究所合作完成的
发表与MIA

2.创新与目的

目的:是为了在domain adaption 上实现创新
创新:提出了Task model(T 分割模型) ,a set of autoencoder (AEs 相似度测量),a set of Adaptors(As transform test image and features to be similar to the source.)
T 和AEs 就是在 source domain 上学习,然后 Adaptors 在 target domain 上学习

3.网络架构

为什么使用autoencoder作为相似度度量了? 这里采取了异常检测相似的思想Gong et al. (2019),的
源训练数据被认为正常,域移测试数据被认为异常。等于说用Autoencoder 代替了神经网络或者是距离函数 作为比较两张图片之间距离的方法

训练阶段:用来训练T 和Adaptor
在这里插入图片描述
测试阶段:
在这里插入图片描述

这其实是将U-ent拆解出来了,大家可以看到测试阶段的A1 到 A3 和 Ax 其实就是adaptor,用来减少AE的误差,其实我们就可以看成是相对其他方法的多维度的使用AE 减少距离
Ax transforms input test image xt to minimize thereconstruction loss from AEx,

loss:多层的L2 loss之和
在这里插入图片描述

4.问题与解决方法

  1. 如何避免特征幻觉(feature hallucination)geometry shift
    在这里插入图片描述

  2. 我们如何使适配器可以通过单个测试对象进行训练?
    为什么用1*1? 卷积的方向模糊也会导致解剖边界位移,影响边界敏感的分割任务,如视网膜层分割。
    (雾 感觉这一块理解的不太好)

  3. 重构能力太强导致所有的结果都离得很近无法分割
    写了一堆 看起来就是加了个偏置,同时需要保证转变前后的距离不变。
    在这里插入图片描述
    不懂为啥这么做。。。

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
Autoencoder-based data augmentation can have a significant influence on deep learning-based wireless communication systems. By generating additional training data through data augmentation, the performance of deep learning models can be greatly improved. This is particularly important in wireless communication systems, where the availability of large amounts of labeled data is often limited. Autoencoder-based data augmentation techniques can be used to generate synthetic data that is similar to the real-world data. This can help to address the problem of overfitting, where the deep learning model becomes too specialized to the training data and performs poorly on new, unseen data. By increasing the diversity of the training data, the deep learning model is better able to generalize to new data and improve its performance. Furthermore, autoencoder-based data augmentation can also be used to improve the robustness of deep learning models to channel variations and noise. By generating synthetic data that simulates different channel conditions and noise levels, the deep learning model can be trained to be more resilient to these factors. This can result in improved performance in real-world wireless communication scenarios, where channel conditions and noise levels can vary widely. In conclusion, autoencoder-based data augmentation can have a significant influence on deep learning-based wireless communication systems by improving the performance and robustness of deep learning models.
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值