# Looking for change? Roll the Dice and demand Attention

arXiv: https://arxiv.org/abs/2009.02062 · HTML: https://mlsanity.com/paper/2009.02062/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Sep 2020.

## Built on by (most cited first, 15 of 15)

- [Remote Sensing Image Change Detection with Transformers](https://mlsanity.com/paper/2103.00208/) (2021)
- [MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining](https://mlsanity.com/paper/2403.13430/) (2024)
- [Revisiting Consistency Regularization for Semi-supervised Change Detection in Remote Sensing Images](https://mlsanity.com/paper/2204.08454/) (2022)
- [FCCDN: Feature Constraint Network for VHR Image Change Detection](https://mlsanity.com/paper/2105.10860/) (2021)
- [ABCNet: Attentive Bilateral Contextual Network for Efficient Semantic Segmentation of Fine-Resolution Remote Sensing Images](https://mlsanity.com/paper/2102.02531/) (2021)
- [Unlocking large-scale crop field delineation in smallholder farming systems with transfer learning and weak supervision](https://mlsanity.com/paper/2201.04771/) (2022)
- [Exchanging Dual Encoder-Decoder: A New Strategy for Change Detection with Semantic Guidance and Spatial Localization](https://mlsanity.com/paper/2311.11302/) (2023)
- [Semantic-aware Dense Representation Learning for Remote Sensing Image Change Detection](https://mlsanity.com/paper/2205.13769/) (2022)
- [VcT: Visual change Transformer for Remote Sensing Image Change Detection](https://mlsanity.com/paper/2310.11417/) (2023)
- [Continuous Cross-resolution Remote Sensing Image Change Detection](https://mlsanity.com/paper/2305.14722/) (2023)
- [PRUE: A Practical Recipe for Field Boundary Segmentation at Scale](https://mlsanity.com/paper/2603.27101/) (2026)
- [Training-free AI for Earth Observation Change Detection using Physics Aware Neuromorphic Networks](https://mlsanity.com/paper/2506.04285/) (2025)
- [MASNet:Improve Performance of Siamese Networks with Mutual-attention for Remote Sensing Change Detection Tasks](https://mlsanity.com/paper/2206.02331/) (2022)
- [SSG2: A new modelling paradigm for semantic segmentation](https://mlsanity.com/paper/2310.08671/) (2023)
- [Tackling fluffy clouds: robust agricultural field boundary delineation from Sentinel-1 and Sentinel-2 satellite image time series](https://mlsanity.com/paper/2409.13568/) (2024)

## Abstract (arXiv)

Change detection, i.e. 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 reliable deep learning framework for the task of semantic change detection in very high-resolution aerial images. Our framework consists of a new loss function, new attention modules, 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 spatial and channel convolution Attention layer (the FracTAL). The new attention layer, designed specifically for vision tasks, is memory efficient, thus suitable for use in all levels of deep convolutional networks. Based on these, we introduce two new efficient self-contained feature extraction convolution units. We validate the performance of these feature extraction building blocks on the CIFAR10 reference data and compare the results with standard ResNet modules. Further, we introduce a new encoder/decoder scheme, a network macro-topology, that is tailored for the task of change detection. Our network moves away from any notion of subtraction of feature layers for identifying change. We validate our approach by showing excellent performance and achieving state of the art score (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.