Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Porgali, Bilal"'
This paper introduces a new large consent-driven dataset aimed at assisting in the evaluation of algorithmic bias and robustness of computer vision and audio speech models in regards to 11 attributes that are self-provided or labeled by trained annot
Externí odkaz:
http://arxiv.org/abs/2303.04838
Autor:
Hazirbas, Caner, Bang, Yejin, Yu, Tiezheng, Assar, Parisa, Porgali, Bilal, Albiero, Vítor, Hermanek, Stefan, Pan, Jacqueline, McReynolds, Emily, Bogen, Miranda, Fung, Pascale, Ferrer, Cristian Canton
Developing robust and fair AI systems require datasets with comprehensive set of labels that can help ensure the validity and legitimacy of relevant measurements. Recent efforts, therefore, focus on collecting person-related datasets that have carefu
Externí odkaz:
http://arxiv.org/abs/2211.05809