Towards zero-shot learning in 3D change detection: improving generalization with custom augmentations and evaluation

Detecting and quantifying changes is crucial for monitoring transformations of the Earth’s surface. It is thus essential to employ methods that can effectively retrieve both 2D and 3D changes over time. The MultiTask Bitemporal Images Transformer (MTBIT) was recently introduced to tackle 2D and 3D C...

Full description

Saved in:
Bibliographic Details
Main Authors: Riccardo Contu, Valerio Marsocci, Virginia Coletta, Roberta Ravanelli, Simone Scardapane
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:European Journal of Remote Sensing
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/22797254.2025.2453468
Tags: Add Tag
No Tags, Be the first to tag this record!