Abstract: Applying a deep learning-based model for medical image segmentation on resource-constrained devices involves substantial challenges. This task demands a model with decreased parameters and ...

Referring Image Segmentation (RIS) is a vision-language task that identifies and segments objects in images based on free-form text descriptions. This study investigates effective data augmentation ...

Abstract: To address four typical stitching distortions (blur, ghosting, geometric distortion, and color distortion)—induced by source image differences and stitching algorithm limitations— and the ...