Adversarial hubs can be generated to be retrieved as top-1 for over 84% of test queries in text-to-image retrieval, far exceeding natural hubs.
The hubness phenomenon: Fact or artifact? Towards Advanced Data Analysis by Com- bining Soft Computing and Statistics , pages 267–278
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Adversarial Hubness in Multi-Modal Retrieval
Adversarial hubs can be generated to be retrieved as top-1 for over 84% of test queries in text-to-image retrieval, far exceeding natural hubs.