Robust and Explainable Fine-Grained Visual Classification with Transfer Learning: A Dual-Carriageway Framework

Z Zuo, J Smith, J Stonehouse… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
In the realm of practical fine-grained visual classification applications rooted in deep
learning a common scenario involves training a model using a pre-existing dataset …

An Augmentation-based Model Re-adaptation Framework for Robust Image Segmentation

Z Zuo, J Smith, J Stonehouse, B Obara - arXiv preprint arXiv:2409.09530, 2024 - arxiv.org
Image segmentation is a crucial task in computer vision, with wide-ranging applications in
industry. The Segment Anything Model (SAM) has recently attracted intensive attention; …

[PDF][PDF] Improving boundary alignment by regularizing superpixels in encoder-decoder models

J de Jong - research.tue.nl
Fully convolutional networks (FCNs) have proven effective at the task of semantic
segmentation. FCNs and succeeding models employ an encoder-decoder structure …