Papers › SFA-Net: Semantic Feature Adjustment Network for Remote Sensing Image Segmentation

SFA-Net: Semantic Feature Adjustment Network for Remote Sensing Image Segmentation

3 Sep 2024Remote Sensing 2024 9archive 2025-07-28

Gyutae Hwang, Jiwoo Jeong, Sang Jun Lee

Advances in deep learning and computer vision techniques have made impacts in the field of remote sensing, enabling efficient data analysis for applications such as land cover classification and change detection. Convolutional neural networks (CNNs) and transformer architectures have been utilized in visual perception algorithms due to their effectiveness in analyzing local features and global context. In this paper, we propose a hybrid transformer architecture that consists of a CNN-based encoder and transformer-based decoder. We propose a feature adjustment module that refines the multiscale feature maps extracted from an EfficientNet backbone network. The adjusted feature maps are integrated into the transformer-based decoder to perform the semantic segmentation of the remote sensing images. This paper refers to the proposed encoder–decoder architecture as a semantic feature adjustment network (SFA-Net). To demonstrate the effectiveness of the SFA-Net, experiments were thoroughly conducted with four public benchmark datasets, including the UAVid, ISPRS Potsdam, ISPRS Vaihingen, and LoveDA datasets. The proposed model achieved state-of-the-art accuracy on the UAVid, ISPRS Vaihingen, and LoveDA datasets for the segmentation of the remote sensing images. On the ISPRS Potsdam dataset, our method achieved comparable accuracy to the latest model while reducing the number of trainable parameters from 113.8 M to 10.7 M.

Paper PDF Code

Code

j2jeong/priv mentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Change Detection Decoder Image Segmentation Land Cover Classification Semantic Segmentation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Semantic Segmentation	Fine-Grained Cloud Segmentation Dataset	SFA-Net	mIoU	74.88	#2 of 4	Archive leaderboard	report
Semantic Segmentation	Fine-Grained Grass Segmentation Dataset	SFA-Net	mIoU	51.21	#2 of 10	Archive leaderboard	report
Semantic Segmentation	ISPRS Potsdam	SFA-Net	Mean F1	93.5	#19 of 20	Archive leaderboard	report
Semantic Segmentation	ISPRS Vaihingen	SFA-Net	Average F1	91.2	#12 of 12	Archive leaderboard	report
Semantic Segmentation	LoveDA	SFA-Net	Category mIoU	54.9	#3 of 19	Archive leaderboard	report
Semantic Segmentation	UAVid	SFA-Net	Mean IoU	70.4	#4 of 10	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 Convolution Average Pooling Batch Normalization Convolution Dense Connections Depthwise Convolution Depthwise Separable Convolution Dropout EfficientNet Inverted Residual Block Pointwise Convolution RMSProp ReLU Sigmoid Activation Squeeze-and-Excitation Block

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections