• Home
  • Search
  • Looking for Change? Roll the Dice and Demand Attention
  • Open Access IconOpen Access
  • Cite Icon75
  • https://doi.org/10.3390/rs13183707Copy DOI Icon

Looking for Change? Roll the Dice and Demand Attention

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Change detection, i.e., the identification per pixel of changes for some classes of interest from a set of bi-temporal co-registered images, is a fundamental task in the field of remote sensing. It remains challenging due to unrelated forms of change that appear at different times in input images. Here, we propose a deep learning framework for the task of semantic change detection in very high-resolution aerial images. Our framework consists of a new loss function, a new attention module, new feature extraction building blocks, and a new backbone architecture that is tailored for the task of semantic change detection. Specifically, we define a new form of set similarity that is based on an iterative evaluation of a variant of the Dice coefficient. We use this similarity metric to define a new loss function as well as a new, memory efficient, spatial and channel convolution Attention layer: the FracTAL. We introduce two new efficient self-contained feature extraction convolution units: the CEECNet and FracTALResNet units. Further, we propose a new encoder/decoder scheme, a network macro-topology, that is tailored for the task of change detection. The key insight in our approach is to facilitate the use of relative attention between two convolution layers in order to fuse them. We validate our approach by showing excellent performance and achieving state-of-the-art scores (F1 and Intersection over Union-hereafter IoU) on two building change detection datasets, namely, the LEVIRCD (F1: 0.918, IoU: 0.848) and the WHU (F1: 0.938, IoU: 0.882) datasets.

Loading PDF

Similar Papers
  • Research Article
  • Citations76

Working Memory Impairment Across Psychotic disorders.

  • Sep 26, 2018
  • Schizophrenia Bulletin
  • James M Gold +8
  • Research Article
  • Citations49

Is the n-back task a measure of unstructured working memory capacity? Towards understanding its connection to other working memory tasks

  • Aug 19, 2021
  • Acta Psychologica
  • Adam Frost +5
  • Research Article
  • Citations142

Change detection using deep learning approach with object-based image analysis

  • Jan 23, 2021
  • Remote Sensing of Environment
  • Tao Liu +2
  • Research Article
  • Citations9

Small object change detection in UAV imagery via a Siamese network enhanced with temporal mutual attention and contextual features: A case study concerning solar water heaters

  • Sep 25, 2024
  • ISPRS Journal of Photogrammetry and Remote Sensing
  • Shikang Tao +4
  • Research Article
  • Citations16

People have the power: priority of socially relevant stimuli in a change detection task

  • Nov 28, 2008
  • Cognitive Processing
  • Fabrizio Bracco +1
  • Research Article
  • Citations3

The properties of visual short-term memory on change detection task

  • Jan 01, 2003
  • Shinrigaku kenkyu : The Japanese journal of psychology
  • Makoto Ozeki +1
  • Research Article
  • Citations77

Encoding strategy accounts for individual differences in change detection measures of VSTM

  • Dec 03, 2010
  • Neuropsychologia
  • A.C Linke +3
  • PDF
  • Research Article
  • Citations2

The impacts of training on change deafness and build-up in a flicker task

  • Nov 17, 2022
  • PLOS ONE
  • Natalie Ball +3
  • Research Article
  • Citations39

The roles of encoding, retrieval, and awareness

  • Jun 01, 2007
  • Memory & Cognition
  • Melissa R Beck +2
  • Research Article
  • Citations17

Coupled dictionary learning for unsupervised change detection between multimodal remote sensing images

  • Sep 02, 2019
  • Computer Vision and Image Understanding
  • Vinicius Ferraris +4
  • Research Article
  • Citations209

Bi-Temporal Semantic Reasoning for the Semantic Change Detection in HR Remote Sensing Images

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Lei Ding +5
  • Research Article
  • Citations19

Successful training of filtering mechanisms in multiple object tracking does not transfer to filtering mechanisms in a visual working memory task: Behavioral and electrophysiological evidence

  • Jun 18, 2012
  • Neuropsychologia
  • Anna M Arend +1
  • Research Article
  • Citations27

Spectral mapping with adversarial learning for unsupervised hyperspectral change detection

  • Sep 06, 2021
  • Neurocomputing
  • Jie Lei +4
  • Research Article
  • Citations71

Exchange means change: An unsupervised single-temporal change detection framework based on intra- and inter-image patch exchange

  • Nov 08, 2023
  • ISPRS Journal of Photogrammetry and Remote Sensing
  • Hongruixuan Chen +4
  • Conference Article
  • Citations1

Spatio-Temporal Neural Network with Dilated Retrospective Convolution for Short-Time Change Detection

  • Apr 01, 2019
  • Chao Chen +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.