| Is it time to replace cnns with transformers for medical images? C Matsoukas, JF Haslum, M Söderberg, K Smith arXiv preprint arXiv:2108.09038, 2021 | 268 | 2021 |
| What makes transfer learning work for medical images: Feature reuse & other factors C Matsoukas, JF Haslum, M Sorkhei, M Söderberg, K Smith Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022 | 174 | 2022 |
| Are natural domain foundation models useful for medical image classification? JP Huix, AR Ganeshan, JF Haslum, M Söderberg, C Matsoukas, K Smith Proceedings of the IEEE/CVF winter conference on applications of computer …, 2024 | 78 | 2024 |
| Patchdropout: Economizing vision transformers using patch dropout Y Liu, C Matsoukas, F Strand, H Azizpour, K Smith Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2023 | 57 | 2023 |
| The spectral nature of Titan's major geomorphological units: Constraints on surface composition A Solomonidou, A Coustenis, RMC Lopes, MJ Malaska, S Rodriguez, ... Journal of Geophysical Research: Planets 123 (2), 489-507, 2018 | 45 | 2018 |
| Pretrained vits yield versatile representations for medical images C Matsoukas, JF Haslum, M Söderberg, K Smith arXiv preprint arXiv:2303.07034, 2023 | 29* | 2023 |
| Adding seemingly uninformative labels helps in low data regimes C Matsoukas, AB Hernandez, Y Liu, K Dembrower, G Miranda, E Konuk, ... International Conference on Machine Learning, 6775-6784, 2020 | 29 | 2020 |
| The chemical composition of impact craters on Titan-I. Implications for exogenic processing A Solomonidou, C Neish, A Coustenis, M Malaska, A Le Gall, RMC Lopes, ... Astronomy & Astrophysics 641, A16, 2020 | 28 | 2020 |
| Spectral and emissivity analysis of the raised ramparts around Titan's northern lakes A Solomonidou, A Le Gall, MJ Malaska, SPD Birch, RMC Lopes, ... Icarus 344, 113338, 2020 | 27 | 2020 |
| Metadata-guided consistency learning for high content images JF Haslum, C Matsoukas, KJ Leuchowius, E Müllers, K Smith Medical Imaging with Deep Learning, 918-936, 2024 | 13 | 2024 |
| Bridging generalization gaps in high content imaging through online self-supervised domain adaptation JF Haslum, C Matsoukas, KJ Leuchowius, K Smith Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2024 | 12 | 2024 |
| Detailed chemical composition analysis of the Soi crater region on Titan A Solomonidou, MJ Malaska, RMC Lopes, A Coustenis, AM Schoenfeld, ... Icarus 421, 116215, 2024 | 2 | 2024 |
| Apla: A simple adaptation method for vision transformers M Sorkhei, E Konuk, K Smith, C Matsoukas arXiv preprint arXiv:2503.11335, 2025 | 1 | 2025 |
| Learning from offline foundation features with tensor augmentations E Konuk, C Matsoukas, M Sorkhei, P Lertsiravarameth, K Smith Advances in Neural Information Processing Systems 37, 120103-120123, 2024 | 1 | 2024 |
| The raised ramparts around Titan's northern lakes A Solomonidou, A Le Gall, M Malaska, S Birch, R Lopes, A Coustenis, ... EGU General Assembly Conference Abstracts, 9493, 2019 | 1 | 2019 |
| Learning What Helps: Task-Aligned Context Selection for Vision Tasks J Guo, E Konuk, F Strand, C Matsoukas, K Smith arXiv preprint arXiv:2512.00489, 2025 | | 2025 |
| k-NN as a Simple and Effective Estimator of Transferability M Sorkhei, C Matsoukas, JF Haslum, E Konuk, K Smith arXiv preprint arXiv:2503.18528, 2025 | | 2025 |
| Efficient Self-Supervised Adaptation for Medical Image Analysis M Sorkhei, E Konuk, J Guo, C Meng, C Matsoukas, K Smith Proceedings of the IEEE/CVF International Conference on Computer Vision, 873-880, 2025 | | 2025 |
| Random Token Fusion for Multi-View Medical Diagnosis J Guo, C Matsoukas, F Strand, K Smith arXiv preprint arXiv:2410.15847, 2024 | | 2024 |
| Streamlining the Histopathological Workflow in Diabetic Kidney Disease with Artificial Intelligence C Matsoukas, TT Tomic, P Tonelius, E Nuñez-Duran, L Liang, ... Journal of the American Society of Nephrology, 10.1681, 2024 | | 2024 |
Kevin SmithProfessor, KTH Royal Institute of Technology & Science for Life LaboratoryVerified email at kth.se
