Convolution and Attention Mixer for Synthetic Aperture Radar Image Change Detection

TL;DR

This paper introduces CAMixer, a novel neural network architecture combining convolution and self-attention for improved SAR image change detection, effectively capturing both local and global features.

Contribution

The paper proposes CAMixer, a Transformer-inspired model that integrates shift convolution with self-attention and a gating mechanism for enhanced SAR change detection.

Findings

CAMixer outperforms existing methods on three SAR datasets.

The parallel design captures both local and global features effectively.

Gating mechanism improves feature representation against noise.

Abstract

Synthetic aperture radar (SAR) image change detection is a critical task and has received increasing attentions in the remote sensing community. However, existing SAR change detection methods are mainly based on convolutional neural networks (CNNs), with limited consideration of global attention mechanism. In this letter, we explore Transformer-like architecture for SAR change detection to incorporate global attention. To this end, we propose a convolution and attention mixer (CAMixer). First, to compensate the inductive bias for Transformer, we combine self-attention with shift convolution in a parallel way. The parallel design effectively captures the global semantic information via the self-attention and performs local feature extraction through shift convolution simultaneously. Second, we adopt a gating mechanism in the feed-forward network to enhance the non-linear feature transformation. The gating mechanism is formulated as the element-wise multiplication of two parallel linear layers. Important features can be highlighted, leading to high-quality representations against speckle noise. Extensive experiments conducted on three SAR datasets verify the superior performance of the proposed CAMixer. The source codes will be publicly available at https://github.com/summitgao/CAMixer .