4 citations · 5 across the 7 of their papers we have counts for
7 papers
Learning What Helps: Task-Aligned Context Selection for Vision Tasks
Jingyu Guo, Emir Konuk, Fredrik Strand +2
Humans often resolve visual uncertainty by comparing an image with relevant examples, but ViTs lack the ability to identify which examples would improve their predictions. We prese…
Efficient Self-Supervised Adaptation for Medical Image Analysis
Moein Sorkhei, Emir Konuk, Jingyu Guo +3
Self-supervised adaptation (SSA) improves foundation model transfer to medical domains but is computationally prohibitive. Although parameter efficient fine-tuning methods such as…
k-NN as a Simple and Effective Estimator of Transferability
Moein Sorkhei, Christos Matsoukas, Johan Fredin Haslum +2
How well can one expect transfer learning to work in a new setting where the domain is shifted, the task is different, and the architecture changes? Many transfer learning metrics…
Random Token Fusion for Multi-View Medical Diagnosis
Jingyu Guo, Christos Matsoukas, Fredrik Strand +1
In multi-view medical diagnosis, deep learning-based models often fuse information from different imaging perspectives to improve diagnostic performance. However, existing approach…
Learning from Offline Foundation Features with Tensor Augmentations
Emir Konuk, Christos Matsoukas, Moein Sorkhei +2
We introduce Learning from Offline Foundation Features with Tensor Augmentations (LOFF-TA), an efficient training scheme designed to harness the capabilities of foundation models i…
Bridging Generalization Gaps in High Content Imaging Through Online Self-Supervised Domain Adaptation
Johan Fredin Haslum, Christos Matsoukas, Karl-Johan Leuchowius +1
High Content Imaging (HCI) plays a vital role in modern drug discovery and development pipelines, facilitating various stages from hit identification to candidate drug characteriza…
Are Natural Domain Foundation Models Useful for Medical Image Classification?
Joana Palés Huix, Adithya Raju Ganeshan, Johan Fredin Haslum +3
The deep learning field is converging towards the use of general foundation models that can be easily adapted for diverse tasks. While this paradigm shift has become common practic…