Saved in:
Bibliographic Details
Main Authors: Kiruluta, Andrew, Lundy, Eric, Lemos, Andreas
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.10619
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909595092385792
author Kiruluta, Andrew
Lundy, Eric
Lemos, Andreas
author_facet Kiruluta, Andrew
Lundy, Eric
Lemos, Andreas
contents We present a unified change detection pipeline that combines instance level masking, multi\-scale attention within a denoising diffusion model, and per pixel semantic classification, all refined via SSIM to match human perception. By first isolating only temporally novel objects with Mask R\-CNN, then guiding diffusion updates through hierarchical cross attention to object and global contexts, and finally categorizing each pixel into one of C change types, our method delivers detailed, interpretable multi\-class maps. It outperforms traditional differencing, Siamese CNNs, and GAN\-based detectors by 10\-25 points in F1 and IoU on both synthetic and real world benchmarks, marking a new state of the art in remote sensing change detection.
format Preprint
id arxiv_https___arxiv_org_abs_2408_10619
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Hierarchical Attention Diffusion Networks with Object Priors for Video Change Detection
Kiruluta, Andrew
Lundy, Eric
Lemos, Andreas
Computer Vision and Pattern Recognition
Artificial Intelligence
Image and Video Processing
We present a unified change detection pipeline that combines instance level masking, multi\-scale attention within a denoising diffusion model, and per pixel semantic classification, all refined via SSIM to match human perception. By first isolating only temporally novel objects with Mask R\-CNN, then guiding diffusion updates through hierarchical cross attention to object and global contexts, and finally categorizing each pixel into one of C change types, our method delivers detailed, interpretable multi\-class maps. It outperforms traditional differencing, Siamese CNNs, and GAN\-based detectors by 10\-25 points in F1 and IoU on both synthetic and real world benchmarks, marking a new state of the art in remote sensing change detection.
title Hierarchical Attention Diffusion Networks with Object Priors for Video Change Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Image and Video Processing
url https://arxiv.org/abs/2408.10619