# RDP-Net: Region Detail Preserving Network for Change Detection

arXiv: https://arxiv.org/abs/2202.09745 · HTML: https://mlsanity.com/paper/2202.09745/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 58 references that are in the map.
- First posted on arXiv 20 Feb 2022.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Benchmarking Graph Neural Networks](https://mlsanity.com/paper/2003.00982/) (2020)
- [Fully Convolutional Siamese Networks for Change Detection](https://mlsanity.com/paper/1810.08462/) (2018)
- [UnitBox: An Advanced Object Detection Network](https://mlsanity.com/paper/1608.01471/) (2016)
- [Patches Are All You Need?](https://mlsanity.com/paper/2201.09792/) (2022)
- [Boundary loss for highly unbalanced segmentation](https://mlsanity.com/paper/1812.07032/) (2018)
- [Urban Change Detection for Multispectral Earth Observation Using Convolutional Neural Networks](https://mlsanity.com/paper/1810.08468/) (2018)
- [DASNet: Dual attentive fully convolutional siamese networks for change detection of high resolution satellite images](https://mlsanity.com/paper/2003.03608/) (2020)
- [Differentiable Learning-to-Normalize via Switchable Normalization](https://mlsanity.com/paper/1806.10779/) (2018)
- [Unsupervised Change Detection in Multi-temporal VHR Images Based on Deep Kernel PCA Convolutional Mapping Network](https://mlsanity.com/paper/1912.08628/) (2019)

## Built on by (most cited first, 13 of 13)

- [MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining](https://mlsanity.com/paper/2403.13430/) (2024)
- [Changen2: Multi-Temporal Remote Sensing Generative Change Foundation Model](https://mlsanity.com/paper/2406.17998/) (2024)
- [Self-Pair: Synthesizing Changes from Single Source for Object Change Detection in Remote Sensing Imagery](https://mlsanity.com/paper/2212.10236/) (2022)
- [MaskCD: A Remote Sensing Change Detection Network Based on Mask Classification](https://mlsanity.com/paper/2404.12081/) (2024)
- [Visual Instruction Pretraining for Domain-Specific Foundation Models](https://mlsanity.com/paper/2509.17562/) (2025)
- [MineNetCD: A Benchmark for Global Mining Change Detection on Remote Sensing Imagery](https://mlsanity.com/paper/2407.03971/) (2024)
- [ChangeMinds: Multi-task Framework for Detecting and Describing Changes in Remote Sensing](https://mlsanity.com/paper/2410.10047/) (2024)
- [SRC-Net: Bi-Temporal Spatial Relationship Concerned Network for Change Detection](https://mlsanity.com/paper/2406.05668/) (2024)
- [Non-Registration Change Detection: A Novel Change Detection Task and Benchmark Dataset](https://mlsanity.com/paper/2505.09939/) (2025)
- [EuroMineNet: A Multitemporal Sentinel-2 Benchmark for Spatiotemporal Mining Footprint Analysis in the European Union (2015-2024)](https://mlsanity.com/paper/2510.14661/) (2025)
- [Remote Sensing Image Change Detection with Graph Interaction](https://mlsanity.com/paper/2307.02007/) (2023)
- [DAM-Net: Domain Adaptation Network with Micro-Labeled Fine-Tuning for Change Detection](https://mlsanity.com/paper/2504.13748/) (2025)
- [JL1-CC&QA: Extending the JL1-CD Benchmark with Change Captioning and Question Answering](https://mlsanity.com/paper/2606.31745/) (2026)

## Abstract (arXiv)

Change detection (CD) is an essential earth observation technique. It captures the dynamic information of land objects. With the rise of deep learning, convolutional neural networks (CNN) have shown great potential in CD. However, current CNN models introduce backbone architectures that lose detailed information during learning. Moreover, current CNN models are heavy in parameters, which prevents their deployment on edge devices such as UAVs. In this work, we tackle this issue by proposing RDP-Net: a region detail preserving network for CD. We propose an efficient training strategy that constructs the training tasks during the warmup period of CNN training and lets the CNN learn from easy to hard. The training strategy enables CNN to learn more powerful features with fewer FLOPs and achieve better performance. Next, we propose an effective edge loss that increases the penalty for errors on details and improves the network's attention to details such as boundary regions and small areas. Furthermore, we provide a CNN model with a brand new backbone that achieves the state-of-the-art empirical performance in CD with only 1.70M parameters. We hope our RDP-Net would benefit the practical CD applications on compact devices and could inspire more people to bring change detection to a new level with the efficient training strategy. The code and models are publicly available at https://github.com/Chnja/RDPNet.