Towards Deep and Efficient: A Deep Siamese Self-Attention Fully Efficient Convolutional Network for Change Detection in VHR Images

TL;DR

This paper introduces EffCDNet, a deep and efficient convolutional network for change detection in very high resolution images, combining novel efficient convolutions, a deep siamese encoder, multi-scale feature capture, and a self-attention decoder to improve accuracy and efficiency.

Contribution

The paper proposes EffCDNet, a novel deep and efficient change detection network that reduces parameters with efficient convolutions and employs a deep siamese encoder and self-attention decoder for improved performance.

Findings

Outperforms state-of-the-art FCN-based methods on challenging datasets.

Uses fewer parameters and has lower computational overhead.

Achieves high accuracy in change detection tasks.

Abstract

Recently, FCNs have attracted widespread attention in the CD field. In pursuit of better CD performance, it has become a tendency to design deeper and more complicated FCNs, which inevitably brings about huge numbers of parameters and an unbearable computational burden. With the goal of designing a quite deep architecture to obtain more precise CD results while simultaneously decreasing parameter numbers to improve efficiency, in this work, we present a very deep and efficient CD network, entitled EffCDNet. In EffCDNet, to reduce the numerous parameters associated with deep architecture, an efficient convolution consisting of depth-wise convolution and group convolution with a channel shuffle mechanism is introduced to replace standard convolutional layers. In terms of the specific network architecture, EffCDNet does not use mainstream UNet-like architecture, but rather adopts the architecture with a very deep encoder and a lightweight decoder. In the very deep encoder, two very deep siamese streams stacked by efficient convolution first extract two highly representative and informative feature maps from input image-pairs. Subsequently, an efficient ASPP module is designed to capture multi-scale change information. In the lightweight decoder, a recurrent criss-cross self-attention (RCCA) module is applied to efficiently utilize non-local similar feature representations to enhance discriminability for each pixel, thus effectively separating the changed and unchanged regions. Moreover, to tackle the optimization problem in confused pixels, two novel loss functions based on information entropy are presented. On two challenging CD datasets, our approach outperforms other SOTA FCN-based methods, with only benchmark-level parameter numbers and quite low computational overhead.