Domain Adaptation Without Source Data

When source domain data can not be accessed decision making procedures are often available for adaptation nevertheless.

Domain adaptation without source data. To avoid accessing source data which may contain sensitive information we. Rules trained on source data and made ready for a direct deployment and later reuse. Data owners and data customers. Unsupervised domain adaptation uda aims to transfer the knowledge learned from labeled source domain to unlabeled target domain.

Prior uda methods typically require to access the source data when learning to adapt the model making them risky and inefficient for decentralized private data. Unsupervised domain adaptation without source data rui li1 qianfen jiao1 wenming cao3 hau san wong1 si wu2 1department of computer science city university of hong kong 2school of computer science and engineering south china university of technology 3department of statistics and actuarial science the university of hong kong. Domain adaptation assumes that samples from source and target domains are freely accessible during a training phase. Unsupervised domain adaptation uda aims to leverage the knowledge learned from a labeled source dataset to solve similar tasks in a new unlabeled domain.

These procedures are often presented in the form of classification identification ranking etc. Sfda domain adaptation without source data sfda train py jump to code definitions seed everything function source fixednet class init function target trainablenet class init function. Existing uda methods require access to the data from the source domain during adaptation to the target domain which may not be feasible in some real world situations. Unsupervised domain adaptation without source data by casting a bait.

Configure virtual anaconda environment. However such an assumption is rarely plausible in real cases and possibly causes data privacy issues especially when the label of the source domain can be a sensitive attribute as an identifier. 0 share. However such an assumption is rarely plausible in real cases and possibly causes data privacy issues especially when the label of the source domain can be a sensitive attribute as an identifier.

Domain adaptation assumes that samples from source and target domains are freely accessible during a training phase. Unsupervised domain adaptation uda aims to transfer the knowledge learned from labeled source domain to unlabeled target domain. This work tackles a practical setting where only a trained source model is. Python 3 6 pytorch 1 5 recent version is recommended nvidia gpu 12gb cuda 10 0 optional cudnn 7 5 optional getting started installation.