Supplementary : Learning to Detect Open Classes for Universal Domain Adaptation

By Bo Fu, Zhangjie Cao, Mingsheng Long, Jianmin Wang. 2020

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Shuaicheng Niu
2. Yunchao Wei
3. Yi Yang
4. Chuang Gan
5. Yifan Zhang
6. Mingkui Tan
7. Guoliang Kang
8. Hongbin Lin

Citations in the corpus

• Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation (2022, methodology): “With various transferability measures, most existing methods conduct domain alignment by quantifying sample-level transferability [9,53].”
• Applications of Unsupervised Deep Transfer Learning to Intelligent Fault Diagnosis: A Survey and Comparative Study (2019, methodology): “Following previous work in [144], [150], [176], [177], five evaluation metrics are employed: 1) Accuracy of shared classes: ALL∗ = MS NS 2) Accuracy of unknown classes: UNK = MU NU 3) Averaged accuracy of all classes: OS = 1 C+1 ∑C c=0Accc 4) Accuracy of all test samples: ALL = MS+MU NS+NU 5) Harmon”
• Domain Consensus Clustering for Universal Domain Adaptation (2021, methodology): “However, as pointed by [17], this measurement is not discriminative and robust enough.”