DomainLab: A modular Python package for domain generalization in deep learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909144885231616 |
|---|---|
| author | Sun, Xudong Feistner, Carla Gossmann, Alexej Schwarz, George Umer, Rao Muhammad Beer, Lisa Rockenschaub, Patrick Shrestha, Rahul Babu Gruber, Armin Chen, Nutan Boushehri, Sayedali Shetab Buettner, Florian Marr, Carsten |
| author_facet | Sun, Xudong Feistner, Carla Gossmann, Alexej Schwarz, George Umer, Rao Muhammad Beer, Lisa Rockenschaub, Patrick Shrestha, Rahul Babu Gruber, Armin Chen, Nutan Boushehri, Sayedali Shetab Buettner, Florian Marr, Carsten |
| contents | Poor generalization performance caused by distribution shifts in unseen domains often hinders the trustworthy deployment of deep neural networks. Many domain generalization techniques address this problem by adding a domain invariant regularization loss terms during training. However, there is a lack of modular software that allows users to combine the advantages of different methods with minimal effort for reproducibility. DomainLab is a modular Python package for training user specified neural networks with composable regularization loss terms. Its decoupled design allows the separation of neural networks from regularization loss construction. Hierarchical combinations of neural networks, different domain generalization methods, and associated hyperparameters, can all be specified together with other experimental setup in a single configuration file. Hierarchical combinations of neural networks, different domain generalization methods, and associated hyperparameters, can all be specified together with other experimental setup in a single configuration file. In addition, DomainLab offers powerful benchmarking functionality to evaluate the generalization performance of neural networks in out-of-distribution data. The package supports running the specified benchmark on an HPC cluster or on a standalone machine. The package is well tested with over 95 percent coverage and well documented. From the user perspective, it is closed to modification but open to extension. The package is under the MIT license, and its source code, tutorial and documentation can be found at https://github.com/marrlab/DomainLab. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_14356 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DomainLab: A modular Python package for domain generalization in deep learning Sun, Xudong Feistner, Carla Gossmann, Alexej Schwarz, George Umer, Rao Muhammad Beer, Lisa Rockenschaub, Patrick Shrestha, Rahul Babu Gruber, Armin Chen, Nutan Boushehri, Sayedali Shetab Buettner, Florian Marr, Carsten Machine Learning Software Engineering Poor generalization performance caused by distribution shifts in unseen domains often hinders the trustworthy deployment of deep neural networks. Many domain generalization techniques address this problem by adding a domain invariant regularization loss terms during training. However, there is a lack of modular software that allows users to combine the advantages of different methods with minimal effort for reproducibility. DomainLab is a modular Python package for training user specified neural networks with composable regularization loss terms. Its decoupled design allows the separation of neural networks from regularization loss construction. Hierarchical combinations of neural networks, different domain generalization methods, and associated hyperparameters, can all be specified together with other experimental setup in a single configuration file. Hierarchical combinations of neural networks, different domain generalization methods, and associated hyperparameters, can all be specified together with other experimental setup in a single configuration file. In addition, DomainLab offers powerful benchmarking functionality to evaluate the generalization performance of neural networks in out-of-distribution data. The package supports running the specified benchmark on an HPC cluster or on a standalone machine. The package is well tested with over 95 percent coverage and well documented. From the user perspective, it is closed to modification but open to extension. The package is under the MIT license, and its source code, tutorial and documentation can be found at https://github.com/marrlab/DomainLab. |
| title | DomainLab: A modular Python package for domain generalization in deep learning |
| topic | Machine Learning Software Engineering |
| url | https://arxiv.org/abs/2403.14356 |