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

08/18/2021
by   Hongruixuan Chen, et al.
9

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.

READ FULL TEXT

page 10

page 12

page 15

page 16

page 21

page 22

research
06/27/2019

Deep Siamese Multi-scale Convolutional Network for Change Detection in Multi-temporal VHR Images

Very high resolution (VHR) images provide abundant ground details and sp...
research
10/25/2021

Highly Efficient Natural Image Matting

Over the last few years, deep learning based approaches have achieved ou...
research
07/01/2020

Automatic Crack Detection on Road Pavements Using Encoder Decoder Architecture

Inspired by the development of deep learning in computer vision and obje...
research
08/05/2018

Self-Attention Recurrent Network for Saliency Detection

Feature maps in deep neural network generally contain different semantic...
research
09/13/2021

CarNet: A Lightweight and Efficient Encoder-Decoder Architecture for High-quality Road Crack Detection

Pixel-wise crack detection is a challenging task because of poor continu...
research
07/08/2020

SiENet: Siamese Expansion Network for Image Extrapolation

Different from image inpainting, image outpainting has relative less con...
research
12/06/2013

Understanding Deep Architectures using a Recursive Convolutional Network

A key challenge in designing convolutional network models is sizing them...

Please sign up or login with your details

Forgot password? Click here to reset