1 code implementation • 21 Nov 2023 • Johan Fredin Haslum, Christos Matsoukas, Karl-Johan Leuchowius, Kevin Smith
CODA can be applied to new, unlabeled out-of-domain data sources of different sizes, from a single plate to multiple experimental batches.
1 code implementation • 30 Oct 2023 • Joana Palés Huix, Adithya Raju Ganeshan, Johan Fredin Haslum, Magnus Söderberg, Christos Matsoukas, Kevin Smith
The deep learning field is converging towards the use of general foundation models that can be easily adapted for diverse tasks.
1 code implementation • 13 Mar 2023 • Christos Matsoukas, Johan Fredin Haslum, Magnus Söderberg, Kevin Smith
Convolutional Neural Networks (CNNs) have reigned for a decade as the de facto approach to automated medical image diagnosis, pushing the state-of-the-art in classification, detection and segmentation tasks.
1 code implementation • 22 Dec 2022 • Johan Fredin Haslum, Christos Matsoukas, Karl-Johan Leuchowius, Erik Müllers, Kevin Smith
High content imaging assays can capture rich phenotypic response data for large sets of compound treatments, aiding in the characterization and discovery of novel drugs.
1 code implementation • 10 Aug 2022 • Yue Liu, Christos Matsoukas, Fredrik Strand, Hossein Azizpour, Kevin Smith
This simple approach, PatchDropout, reduces FLOPs and memory by at least 50% in standard natural image datasets such as ImageNet, and those savings only increase with image size.
1 code implementation • CVPR 2022 • Christos Matsoukas, Johan Fredin Haslum, Moein Sorkhei, Magnus Söderberg, Kevin Smith
Transfer learning is a standard technique to transfer knowledge from one domain to another.
no code implementations • 29 Sep 2021 • Christos Matsoukas, Johan Fredin Haslum, Moein Sorkhei, Magnus Soderberg, Kevin Smith
Convolutional Neural Networks (CNNs) have reigned for a decade as the de facto approach to automated medical image diagnosis, pushing the state-of-the-art in classification, detection and segmentation tasks.
1 code implementation • 20 Aug 2021 • Christos Matsoukas, Johan Fredin Haslum, Magnus Söderberg, Kevin Smith
Convolutional Neural Networks (CNNs) have reigned for a decade as the de facto approach to automated medical image diagnosis.
2 code implementations • ICML 2020 • Christos Matsoukas, Albert Bou I Hernandez, Yue Liu, Karin Dembrower, Gisele Miranda, Emir Konuk, Johan Fredin Haslum, Athanasios Zouzos, Peter Lindholm, Fredrik Strand, Kevin Smith
Evidence suggests that networks trained on large datasets generalize well not solely because of the numerous training examples, but also class diversity which encourages learning of enriched features.