Electrical engineering

Architecture

Pattern recognition (psychology)

Computer network

Operating system

Encoder

Engineering

Visual arts

Voltage

Artificial intelligence

Network architecture

Set (abstract data type)

Programming language

Code (set theory)

Computer science

Transformer

Convolutional neural network

This paper presents a transformer-based Siamese network architecture (abbreviated by ChangeFormer) for Change Detection (CD) from a pair of co-registered remote sensing images. Different from recent CD frameworks, which are based on fully convolutional networks (ConvNets), the proposed method unifies hierarchically structured transformer encoder with Multi-Layer Perception (MLP) decoder in a Siamese network architecture to efficiently render multi-scale long-range details required for accurate CD. Experiments on two CD datasets show that the proposed end-to-end trainable ChangeFormer architecture achieves better CD performance than previous counterparts. Our code and pre-trained models are available at github.com/wgcban/ChangeFormer.

A Transformer-Based Siamese Network for Change Detection