RDP-Net: Region Detail Preserving Network for Change Detection

Abstract

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.

arXiv comment10 pages, 10 figures, 55 references

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Decoupled Weight Decay Regularization
• Improving neural networks by preventing co-adaptation of feature detectors
• Gaussian Error Linear Units (GELUs)
• UnitBox: An Advanced Object Detection Network
• DASNet: Dual attentive fully convolutional siamese networks for change detection of high resolution satellite images
• Boundary loss for highly unbalanced segmentation
• Differentiable Learning-to-Normalize via Switchable Normalization

Cited by in corpus (2)

• Remote Sensing SpatioTemporal Vision-Language Models: A Comprehensive Survey
• SRC-Net: Bi-Temporal Spatial Relationship Concerned Network for Change Detection