SwinV2DNet: Pyramid and Self-Supervision Compounded Feature Learning for Remote Sensing Images Change Detection

TL;DR

SwinV2DNet is an innovative change detection network combining transformer and CNN features with a novel pyramid and self-supervision strategy, achieving state-of-the-art results on remote sensing datasets.

Contribution

The paper introduces SwinV2DNet, a novel end-to-end network that integrates transformer and CNN features with a mixed feature pyramid and self-supervision for improved change detection.

Findings

Achieved state-of-the-art change detection scores.

Provided fine-grained change maps.

Validated effectiveness of MFP module in other networks.

Abstract

Among the current mainstream change detection networks, transformer is deficient in the ability to capture accurate low-level details, while convolutional neural network (CNN) is wanting in the capacity to understand global information and establish remote spatial relationships. Meanwhile, both of the widely used early fusion and late fusion frameworks are not able to well learn complete change features. Therefore, based on swin transformer V2 (Swin V2) and VGG16, we propose an end-to-end compounded dense network SwinV2DNet to inherit the advantages of both transformer and CNN and overcome the shortcomings of existing networks in feature learning. Firstly, it captures the change relationship features through the densely connected Swin V2 backbone, and provides the low-level pre-changed and post-changed features through a CNN branch. Based on these three change features, we accomplish accurate change detection results. Secondly, combined with transformer and CNN, we propose mixed feature pyramid (MFP) which provides inter-layer interaction information and intra-layer multi-scale information for complete feature learning. MFP is a plug and play module which is experimentally proven to be also effective in other change detection networks. Further more, we impose a self-supervision strategy to guide a new CNN branch, which solves the untrainable problem of the CNN branch and provides the semantic change information for the features of encoder. The state-of-the-art (SOTA) change detection scores and fine-grained change maps were obtained compared with other advanced methods on four commonly used public remote sensing datasets. The code is available at https://github.com/DalongZ/SwinV2DNet.