Search Results for author: Kevin Thandiackal

Found 6 papers, 0 papers with code

Multi-scale Feature Alignment for Continual Learning of Unlabeled Domains

no code implementations2 Feb 2023 Kevin Thandiackal, Luigi Piccinelli, Pushpak Pati, Orcun Goksel

Methods for unsupervised domain adaptation (UDA) help to improve the performance of deep neural networks on unseen domains without any labeled data.

Continual Learning Unsupervised Domain Adaptation

Generative appearance replay for continual unsupervised domain adaptation

no code implementations3 Jan 2023 Boqi Chen, Kevin Thandiackal, Pushpak Pati, Orcun Goksel

In contrast to single-step unsupervised domain adaptation (UDA), continual adaptation to a sequence of domains enables leveraging and consolidation of information from multiple domains.

Continual Learning Unsupervised Domain Adaptation

Differentiable Zooming for Multiple Instance Learning on Whole-Slide Images

no code implementations26 Apr 2022 Kevin Thandiackal, Boqi Chen, Pushpak Pati, Guillaume Jaume, Drew F. K. Williamson, Maria Gabrani, Orcun Goksel

Multiple Instance Learning (MIL) methods have become increasingly popular for classifying giga-pixel sized Whole-Slide Images (WSIs) in digital pathology.

Multiple Instance Learning whole slide images

Generative Feature-driven Image Replay for Continual Learning

no code implementations9 Jun 2021 Kevin Thandiackal, Tiziano Portenier, Andrea Giovannini, Maria Gabrani, Orcun Goksel

In this work, we propose Genifer (GENeratIve FEature-driven image Replay), where a generative model is trained to replay images that must induce the same hidden features as real samples when they are passed through the classifier.

Class Incremental Learning Incremental Learning

Artificial Intelligence Decision Support for Medical Triage

no code implementations9 Nov 2020 Chiara Marchiori, Douglas Dykeman, Ivan Girardi, Adam Ivankay, Kevin Thandiackal, Mario Zusag, Andrea Giovannini, Daniel Karpati, Henri Saenz

Applying state-of-the-art machine learning and natural language processing on approximately one million of teleconsultation records, we developed a triage system, now certified and in use at the largest European telemedicine provider.

Cannot find the paper you are looking for? You can Submit a new open access paper.