Código QR (código de barras bidimensional)

Integrated Framework for Unsupervised Building Segmentation with Segment Anything Model-Based Pseudo-Labeling and Weakly Supervised Learning

The Segment Anything Model (SAM) has had a profound impact on deep learning applications in remote sensing. SAM, which serves as a prompt-based foundation model for segmentation, exhibits a remarkable capability to “segment anything,” including building objects on satellite or airborne images. To fa...

Fuld beskrivelse

Na minha lista:
Principais autores: Jiyong Kim, Yongil Kim
Format: Artigo
Sprog:Inglês
Udgivet: MDPI AG 2024-01-01
Serier:Remote Sensing
Fag:
semantic segmentation
unsupervised building extraction
edge-driven model
pseudo-label
Online adgang:https://www.mdpi.com/2072-4292/16/3/526
Tags: Tilføj Tag
Ingen Tags, Vær først til at tagge denne postø!

Lignende værker