Algorithm2Domain - Integrative Benchmarking
Algorithm2Domain is a meta-repository for benchmarking of domain adaptation performance managed by NFDI4DataScience consortium and the Institute for Biomedical Informatics (University Hospital of Cologne). Our goal is to aggregate existing algorithms and benchmarking suits, and develop integrative pipelines for mix-and-match cross-domain benchmarking. The data sources suitable for the benchmarking will be aggregated as pointers.
This repository will contain a integrative benchmarking suite, that connects the datasets, models, domain adaptation algorithms, few-shot approaches and datasets from various domain adaptation benchmarking suites. For now our seed benchmarking suite is ADATime by by: Mohamed Ragab*, Emadeldeen Eldele*, Wee Ling Tan, Chuan-Sheng Foo, Zhenghua Chen☨, Min Wu, Chee Kwoh, Xiaoli Li.
In the Wiki we aggregate knowledge regarding domain adaptation and related topics: generalizability, out-of-distribution performance etc., as well as different methods to improve the algorithm design and to efficiently adapt it to the new domain.
Contact persons: Mayra Elwes (Mayra.Elwes at uk-koeln.de, technical questions), Ekaterina Kutafina (ekaterina.kutafina at uni-koeln.de, collaborations, contributions, development).
The Apache 2.0 license concerns the original code developed in this meta-repository. For sub-repositories and other resources please check the corresponding license agreements.
TODO