English

PPTFormer: Pseudo Multi-Perspective Transformer for UAV Segmentation

Computer Vision and Pattern Recognition 2024-07-12 v2

Abstract

The ascension of Unmanned Aerial Vehicles (UAVs) in various fields necessitates effective UAV image segmentation, which faces challenges due to the dynamic perspectives of UAV-captured images. Traditional segmentation algorithms falter as they cannot accurately mimic the complexity of UAV perspectives, and the cost of obtaining multi-perspective labeled datasets is prohibitive. To address these issues, we introduce the PPTFormer, a novel \textbf{P}seudo Multi-\textbf{P}erspective \textbf{T}rans\textbf{former} network that revolutionizes UAV image segmentation. Our approach circumvents the need for actual multi-perspective data by creating pseudo perspectives for enhanced multi-perspective learning. The PPTFormer network boasts Perspective Representation, novel Perspective Prototypes, and a specialized encoder and decoder that together achieve superior segmentation results through Pseudo Multi-Perspective Attention (PMP Attention) and fusion. Our experiments demonstrate that PPTFormer achieves state-of-the-art performance across five UAV segmentation datasets, confirming its capability to effectively simulate UAV flight perspectives and significantly advance segmentation precision. This work presents a pioneering leap in UAV scene understanding and sets a new benchmark for future developments in semantic segmentation.

Keywords

Cite

@article{arxiv.2406.19632,
  title  = {PPTFormer: Pseudo Multi-Perspective Transformer for UAV Segmentation},
  author = {Deyi Ji and Wenwei Jin and Hongtao Lu and Feng Zhao},
  journal= {arXiv preprint arXiv:2406.19632},
  year   = {2024}
}

Comments

IJCAI 2024

R2 v1 2026-06-28T17:22:11.602Z