CBIR Evaluation on contextually different data

1

How good would a CBIR system trained on a dataset, for example, DELF, trained on the Google Landmarks dataset, perform when evaluated on a contextually different dataset such as the WANG or the COREL dataset without retraining?

Arun George

Posted 2019-09-13T04:21:02.757

Reputation: 111

Hi. You say "trained on a dataset, for example, DELF, trained on the Google Landmarks dataset", but a dataset cannot be trained on another dataset. Please, fix the wording of your post and add links to the relevant datasets and models. – nbro – 2019-09-13T12:51:14.523

No answers