MFSFNet: Multi-Scale Feature Subtraction Fusion Network for Remote Sensing Image Change Detection

Abstract

Change detection plays a crucial role in remote sensing by identifying surface modifications between two sets of temporal remote sensing images. Recent advancements in deep learning techniques have yielded significant achievements in this field. However, there are still some challenges: (1) Existing change feature fusion methods often introduce redundant information. (2) The complexity of network structures leads to a large number of parameters and difficulties in model training. To overcome these challenges, this paper proposes a Multi-Scale Feature Subtraction Fusion Network (MFSF-Net). It comprises two primary modules: the Multi-scale Feature Subtraction Fusion (MFSF) module and the Feature Deep Supervision (FDS) module. MFSF enhances change features and reduces redundant pseudo-change features. FDS provides additional supervision on different scales of change features in the decoder, improving the training efficiency performance of the network. Additionally, to address the problem of imbalanced samples, the Dice loss strategy is introduced as a means to mitigate this issue. Through comprehensive experiments, MFSF-Net achieves an F1 score of 91.15% and 95.64% on LEVIR-CD and CDD benchmark datasets, respectively, outperforming six state-of-the-art algorithms. Moreover, it attains an improved balance between model complexity and performance, showcasing the efficacy of the proposed approach.

Multilevel feature aggregation and enhancement network for remote sensing change detection

“…To evaluate the effectiveness and efficiency of our MFAENet, we select several state-of-the-art (SOTA) models as competitors, including CNNs-based methods: FC-EF, 19 FC-SD, 19 FC-SC, 19 SNUNet, 49 TFI-GR, 45 Changer, 37 MFIN, 56 MFSFNet, 57 CICNet, 58 and two transformer-based methods: BIT 31 and ChangeFormer. 33 We reproduce these models using their publicly available code and default parameters to ensure fair comparisons.…”