QR kód

SwinInsSeg: An Improved SOLOv2 Model Using the Swin Transformer and a Multi-Kernel Attention Module for Ship Instance Segmentation

Maritime surveillance is essential for ensuring security in the complex marine environment. The study presents SwinInsSeg, an instance segmentation model that combines the Swin transformer and a lightweight MKA module to segment ships accurately and efficiently in maritime surveillance. Current mode...

Celý popis

Uloženo v:
Hlavní autoři: Rabi Sharma, Muhammad Saqib, Chin-Teng Lin, Michael Blumenstein
Médium: Artigo
Jazyk:Inglês
Vydáno: MDPI AG 2025-01-01
Edice:Mathematics
Témata:
instance segmentation
maritime surveillance
convolutional neural network
transformers
attention
On-line přístup:https://www.mdpi.com/2227-7390/13/1/165
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Podobné jednotky