本文是关于Domain Adaptation的论文笔记，重点探讨了如何在源域有标签，目标域无标签的情况下，通过深度学习方法学习域不变特征。涉及多种方法，包括Backpropagation、Deep Adaptation Networks、Generative Adversarial Networks等，旨在减少领域间差距，实现无监督或半监督的领域适应。实验部分包括单领域适应和联合领域学习。
Domain Adaptation 论文阅读笔记
文章目录
- Domain Adaptation 论文阅读笔记
- 一、Method Summary
-
- Unsupervised Domain Adaptation by Backpropagation
- Learning Transferable Features with Deep Adaptation Networks
- Coupled Generative Adversarial Networks
- Domain Separation Networks
- DiDA: Disentangled Synthesis for Domain Adaptation
- Unsupervised Domain Adaptation in the Wild via Disentangling Representation Learning
- Unsupervised Domain Adaptation via Disentangled Representations: Application to Cross-Modality Liver Segmentation
- Learning from Synthetic Data: Addressing Domain Shift for Semantic Segmentation
- Contrastive Adaptation Network for Unsupervised Domain Adaptation (CVPR 2019)
- MME: Semi-supervised Domain Adaptation via Minimax Entropy
- PAC: Surprisingly Simple Semi-Supervised Domain Adaptation with Pretraining and Consistency (BMVC 2021)
- Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation
- 2. Experiment part
- 3. Analysis part
What is Domain Adaptation(DA)? — attempt to map representations between the two domains or learn to extract features that are domain–invariant.
source有label，target没有
一、Method Summary
Unsupervised Domain Adaptation by Backpropagation
domian classifier部分的梯度需要通过gradient reverse layer，使encoder提到的信息不利于domain 分类，也就是domain-invariant feature
Learning Transferable Features with Deep Adaptation Networks
(https://blog.youkuaiyun.com/weixin_40526176/article/details/79065861)
- 多层适配
- 适配最后3层——认为（AlexNet）最后3层是task-specific，对于其他网络要另外计算相似度
- Multi kernel-MMD(Maximum Mean Discrepancy)
- 可以用来计算不同域feature的距离，相当于把1中的maximize domain error换成这边的minimize MMD
Coupled Generative Adversarial Networks
- 即便没有labeled cross-domain pair，也可以通过weight sharing和adversarial learning学习到2个domain的joint distribution——相当于输入同一个vector z，2个generator的输出是一对语义相关但是各有特点的pair。
- weight sharing如highlight部分所示，其中z是random vector，因为有了weight sharing，可以保证对应高层语义信息的layer，其处理信息的方式是一致的。
- 这似乎不是DA，但是这个框架可以用在DA上，效果似乎很不错——因为虽然target没有label，但是source有label，并且有weight sharing机制，使得2个generator得到的图像g(z)理论上是同一个数字。
Domain Separation Networks
构建一个直接提取domain-invariant的框架，会导致 these representations might trivially include noise that is highly correlated with the shared representation.
- Overall Loss:
- Reconstruction Loss:
- 用scale mse，因为普通mse
penalizes predictions that are correct up to a scaling term.，而scale msepenalizes differences between pairs of pixels. This allows the model to learn to reproduce the overall shape of the objects being modeled without expending modeling power on the absolute color or intensity of the inputs.（为什么scale会导致model分心？）
- 用scale mse，因为普通mse
最低0.47元/天 解锁文章
扫一扫
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
