Difference between revisions of "MODEL DISENTANGLEMENT FOR DOMAIN ADAPTATION: abstract simplified (17655506)"
Jump to navigation
Jump to search
Wikipatents (talk | contribs) (Creating a new page) |
Wikipatents (talk | contribs) (Creating a new page) |
||
| (One intermediate revision by the same user not shown) | |||
| Line 1: | Line 1: | ||
| − | The abstract describes a technique for improving domain adaptation in machine learning. It involves generating a feature tensor from input data using a feature extractor. This tensor is then processed by both a domain-agnostic classifier and a domain-specific classifier to generate two sets of logits (outputs). A loss function is computed based on these logits, including a divergence loss component. The feature extractor, domain-agnostic classifier, and domain-specific classifier are | + | The abstract describes a technique for improving domain adaptation in machine learning. It involves generating a feature tensor from input data using a feature extractor. This tensor is then processed by both a domain-agnostic classifier and a domain-specific classifier to generate two sets of logits (outputs). A loss function is computed based on these logits, including a divergence loss component. The feature extractor, domain-agnostic classifier, and domain-specific classifier are refined using this loss function. Overall, this technique aims to enhance the ability of machine learning models to adapt to different domains. |
Latest revision as of 16:20, 1 October 2023
The abstract describes a technique for improving domain adaptation in machine learning. It involves generating a feature tensor from input data using a feature extractor. This tensor is then processed by both a domain-agnostic classifier and a domain-specific classifier to generate two sets of logits (outputs). A loss function is computed based on these logits, including a divergence loss component. The feature extractor, domain-agnostic classifier, and domain-specific classifier are refined using this loss function. Overall, this technique aims to enhance the ability of machine learning models to adapt to different domains.
