About this resource
<h2>Initial Release of EDTrans</h2> <p>This is the first public release of EDTrans, accompanying our manuscript submitted to <strong>The Visual Computer (Springer Nature)</strong>:</p> <blockquote> <p>"Boundary-Guided Hybrid CNN-Transformer Architecture for Robust Medical Image Segmentation"</p> </blockquote> <h3>Features</h3> <ul> <li>Edge-Aware Module (EAM) for explicit boundary supervision</li> <li>Dual Attention Module (DAM) with reverse attention</li> <li>Hybrid CNN-Transformer with Spatial Pyramid Pooling</li> <li>Training, evaluation, and inference scripts</li> </ul> <h3>Datasets Supported</h3> <ul> <li>Kvasir-SEG</li> <li>CVC-ClinicDB</li> </ul> <h3>Results</h3> <ul> <li>Dice 90.30% on Kvasir-SEG</li> <li>Dice 93.15% on CVC-ClinicDB</li> </ul>
Files and access
Resources are read online through DARE. Direct file links are not published; access is checked against DSpace when a document is opened. Authorised librarian workflows are unaffected.
This record contains bibliographic metadata, but no files are currently attached.
