Saved in:
Bibliographic Details
Main Authors: Zhang, Da, Junyu, Gao, Zhiyuan, Zhao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.01550
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914439355170816
author Zhang, Da
Junyu, Gao
Zhiyuan, Zhao
author_facet Zhang, Da
Junyu, Gao
Zhiyuan, Zhao
contents Semantic segmentation of low-altitude UAV imagery presents unique challenges due to extreme scale variations, complex object boundaries, and limited computational resources on edge devices. Existing transformer-based segmentation methods achieve remarkable performance but incur high computational overhead, while lightweight approaches struggle to capture fine-grained details in high-resolution aerial scenes. To address these limitations, we propose PBSeg, an efficient prototype-based segmentation framework tailored for UAV applications. PBSeg introduces a novel prototype-based cross-attention (PBCA) that exploits feature redundancy to reduce computational complexity while maintaining segmentation quality. The framework incorporates an efficient multi-scale feature extraction module that combines deformable convolutions (DConv) with context-aware modulation (CAM) to capture both local details and global semantics. Experiments on two challenging UAV datasets demonstrate the effectiveness of the proposed approach. PBSeg achieves 71.86\% mIoU on UAVid and 80.92\% mIoU on UDD6, establishing competitive performance while maintaining computational efficiency. Code is available at https://github.com/zhangda1018/PBSeg.
format Preprint
id arxiv_https___arxiv_org_abs_2604_01550
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Prototype-Based Low Altitude UAV Semantic Segmentation
Zhang, Da
Junyu, Gao
Zhiyuan, Zhao
Computer Vision and Pattern Recognition
Semantic segmentation of low-altitude UAV imagery presents unique challenges due to extreme scale variations, complex object boundaries, and limited computational resources on edge devices. Existing transformer-based segmentation methods achieve remarkable performance but incur high computational overhead, while lightweight approaches struggle to capture fine-grained details in high-resolution aerial scenes. To address these limitations, we propose PBSeg, an efficient prototype-based segmentation framework tailored for UAV applications. PBSeg introduces a novel prototype-based cross-attention (PBCA) that exploits feature redundancy to reduce computational complexity while maintaining segmentation quality. The framework incorporates an efficient multi-scale feature extraction module that combines deformable convolutions (DConv) with context-aware modulation (CAM) to capture both local details and global semantics. Experiments on two challenging UAV datasets demonstrate the effectiveness of the proposed approach. PBSeg achieves 71.86\% mIoU on UAVid and 80.92\% mIoU on UDD6, establishing competitive performance while maintaining computational efficiency. Code is available at https://github.com/zhangda1018/PBSeg.
title Prototype-Based Low Altitude UAV Semantic Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.01550