2 citations · 3 across the 4 of their papers we have counts for
5 papers
Exploring Simple, High Quality Out-of-Distribution Detection with L2 Normalization
Jarrod Haas, William Yolland, Bernhard Rabus
We demonstrate that L2 normalization over feature space can produce capable performance for Out-of-Distribution (OoD) detection for some models and datasets. Although it does not d…
Linking Neural Collapse and L2 Normalization with Improved Out-of-Distribution Detection in Deep Neural Networks
Jarrod Haas, William Yolland, Bernhard Rabus
We propose a simple modification to standard ResNet architectures--L2 normalization over feature space--that substantially improves out-of-distribution (OoD) performance on the pre…
Can self-training identify suspicious ugly duckling lesions?
Mohammadreza Mohseni, Jordan Yap, William Yolland +2
One commonly used clinical approach towards detecting melanomas recognises the existence of Ugly Duckling nevi, or skin lesions which look different from the other lesions on the s…
Out-of-Distribution Detection for Dermoscopic Image Classification
Mohammadreza Mohseni, Jordan Yap, William Yolland +2
Medical image diagnosis can be achieved by deep neural networks, provided there is enough varied training data for each disease class. However, a hitherto unknown disease class not…
Constructions of difference sets in nonabelian 2-groups
Taylor Applebaum, John Clikeman, James A. Davis +5
Difference sets have been studied for more than 80 years. Techniques from algebraic number theory, group theory, finite geometry, and digital communications engineering have been u…