Adversarial Similarity Network for Evaluating Image Alignment in Deep Learning based Registration
一、Motivation 1. 传统的配准方法试图基于基于强度的相似性度量来优化变形场。这些方法通常涉及计算量大的高维优化和与任务有关的参数调整。 2. 最近的基于CNN的有监督配准方法虽然能够一定程度上解决传统方法的缺点，但是受限于ground-truth的真实性。 3. 在无监督的CNN方法利用相似性指标作为损失函数的一部分，这些相似性指标与图像的性质密切相关，可能不适用于处理各种数据集。
相关文章
- 1. 《Adversarial learning for weakly-supervised social network alignment》翻译
- 2. Image Similarity Siamese Network
- 3. Registration小结2
- 4. Deep Residual Learning for Image Recognition
- 5. Image-Image Domain Adaptation with Preserved Self-Similarity andDomain-Dissimilarity for Person Re-i
- 6. Image Detection in deep learning
- 7. Deep Learning and SVM Classification for Plant Recognition in Content-Based Large Scale Image Retrie
- 8. Deep Learning for Chatbots, Part 2 – Implementing a Retrieval-Based Model in Tensorflow
- 9. Deep Alignment Network: A convolutional neural network for robust face alignment
- 10. ResNet--Deep Residual Learning for Image Recognition
- 更多相关文章...
- • Swift for-in 循环 - Swift 教程
- • Lua for 循环 - Lua 教程
- • Flink 数据传输及反压详解
- • Java Agent入门实战（一）-Instrumentation介绍与使用
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. 《Adversarial learning for weakly-supervised social network alignment》翻译
- 2. Image Similarity Siamese Network
- 3. Registration小结2
- 4. Deep Residual Learning for Image Recognition
- 5. Image-Image Domain Adaptation with Preserved Self-Similarity andDomain-Dissimilarity for Person Re-i
- 6. Image Detection in deep learning
- 7. Deep Learning and SVM Classification for Plant Recognition in Content-Based Large Scale Image Retrie
- 8. Deep Learning for Chatbots, Part 2 – Implementing a Retrieval-Based Model in Tensorflow
- 9. Deep Alignment Network: A convolutional neural network for robust face alignment
- 10. ResNet--Deep Residual Learning for Image Recognition