From Same Photo: Cheating on Visual Kinship Challenges
By Mitchell Dawson, Andrew Zisserman, Christoffer Nellåker. 2018
25 citations recorded by the source corpus.
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 cropped from the same photograph, since faces from the same photograph are more likely to be from the same family. In this paper we investigate the influence of this artefactual data inference in published data sets for kinship verification.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Experimental and Cognitive Psychology
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Jörn-Henrik Jacobsen
- Matthias Bethge
- Richard S. Zemel
- Wieland Brendel
- Robert Geirhos
- Claudio Michaelis
- Felix Wichmann
- Yoshua Bengio
In Computer Vision and Pattern Recognition
- Matthias Bethge
- Luc Van Gool
- Wieland Brendel
- Trevor Darrell
- Richard S. Zemel
- Bernt Schiele
- Ming-Hsuan Yang
- Dacheng Tao
In Experimental and Cognitive Psychology
Citations in the corpus
- Shortcut learning in deep neural networks (2020, background): “If cows happen to be on grassland for most of the training data, detecting grass instead of cows becomes a successful strategy for solving a classification problem in an unintended way; and indeed many models base their predictions on context [23, 24, 25, 26, 9, 27, 10].”