no code implementations • 7 Jun 2023 • 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.
no code implementations • 17 Sep 2022 • 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 previously proposed Deep Deterministic Uncertainty (DDU) benchmark.
no code implementations • 15 May 2021 • Mohammadreza Mohseni, Jordan Yap, William Yolland, Arash Koochek, M Stella Atkins
We first automatically detect and extract all the lesions from a wide-field skin image, and calculate an embedding for each detected lesion in a patient image, based on automatically identified features.
no code implementations • 15 Apr 2021 • Mohammadreza Mohseni, Jordan Yap, William Yolland, Majid Razmara, M Stella Atkins
This problem is especially important for medical image diagnosis, when an image of a hitherto unknown disease is presented for diagnosis, especially when the images come from the same image domain, such as dermoscopic skin images.