From same photo: cheating on visual kinship challenges
With the propensity for deep learning models to learn unintended signals from data sets there is always the possibility that the network can `cheat' in order to solve a task. In the instance of data sets for visual kinship verification, one such unintended signal could be that the faces are cro...
Autors principals: | Dawson, M, Zisserman, A, Nellåker, C |
---|---|
Format: | Internet publication |
Idioma: | English |
Publicat: |
2018
|
Ítems similars
-
From same photo: Cheating on visual kinship challenges
per: Dawson, M, et al.
Publicat: (2019) -
Photos provide information on age, but not kinship, of Andean bear
per: Russell C. Van Horn, et al.
Publicat: (2015-07-01) -
Diagnostically relevant facial gestalt information from ordinary photos
per: Ferry, Q, et al.
Publicat: (2014) -
Mining faces from biomedical literature using deep learning
per: Dawson, M, et al.
Publicat: (2017) -
Same cheat, different wrapping: DRG scandals and accountability in Germany and Norway
per: Neby, S, et al.
Publicat: (2013)