Source-Free 近期大致论文整理

下面是个人分类整理的Source-Free的论文列表,非完全,后续将跟踪补充,欢迎各位大佬指导补充!

1.冻结分类器

BAIT(Unsupervised Domain Adaptation without Source Data by Casting a BAIT)

GITHUB:https://github.com/BIT-DA/DCAN

SHOT(Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation)

GitHub:https://github.com/tim-learn/SHOT

2.对抗网络

3C-GAN(Model Adaptation: Unsupervised Domain Adaptation without Source Data)

GITHUB:好像有开源,但是我没找到,欢迎补充。

SDDA(Domain Impression: A Source Data Free Domain Adaptation Method) CVPR2021

GITHUB:

3.伪标签

DECISION(Unsupervised Multi-source Domain Adaptation Without Access to Source Data)CVPR2021

GITHUB:

PRDA(Progressive Domain Adaptation from a Source Pre-trained Model)

GITHUB:https://github.com/youngryan1993/PrDA-Progressive-Domain-Adaptation-from-a-Source-Pre-trained-Model

Noisy Label(Self-Supervised Noisy Label Learning for Source-Free Unsupervised Domain Adaptation)

GITHUB:

4.加权机制

usfda(Universal Source-Free Domain Adaptation)

GITHUB:https://github.com/val-iisc/usfda

CONFIDENCE SCORE WEIGHT(CONFIDENCE SCORE WEIGHTING ADAPTATION FOR SOURCE-FREE UNSUPERVISED DOMAIN ADAPTATION)

GITHUB:

5.知识蒸馏

TRANSDA(Transformer-Based Source-Free Domain Adaptation)

GITHUB:https://github.com/ygjwd12345/TransDA

6.Neighborhood 

G-SFDA(Generalized Source-free Domain Adaptation)

GITHUB:https://github.com/Albert0147/G-SFDA

SFDA_Neighboor(Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation)

GITHUB:https://github.com/Albert0147/SFDA_neighbors

 

上一篇:新版 OPPO Enco Free 2 固件工具 (仅供交流学习使用)


下一篇:linux下buffer和cache的异同及free中shared的含义