10 citations · 11 across the 2 of their papers we have counts for
2 papers
cs.CV2018★ 10 cited
Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddings
Mohsan Alvi, Andrew Zisserman, Christoffer Nellaker
Neural networks achieve the state-of-the-art in image classification tasks. However, they can encode spurious variations or biases that may be present in the training data. For exa…
cs.CV2018★ 1 cited
From Same Photo: Cheating on Visual Kinship Challenges
Mitchell Dawson, Andrew Zisserman, Christoffer Nellåker
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 th…