Siamese Adaptive Transformer Network for Real-Time Aerial Tracking

Daitao Xing, Athanasios Tsoukalas, Nikolaos Evangeliou, Nikolaos Giakoumidis, Anthony Tzes

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Recent visual object trackers provide strong discriminability towards accurate tracking under challenging scenarios while neglecting the inference efficiency. Those methods handle all inputs with identical computation and fail to reduce intrinsic computational redundancy, which constrains their deployment on Unmanned Aerial Vehicles (UAVs). In this work, we propose a dynamic tracker which selectively activates the individual model components and allocates computation resources on demand during the inference, which allows deep network inference on onboard-CPU at real-time speed. The tracking pipeline is divided into several stages, where each stage consists of a transformer-based encoder that generates a robust target representation by learning pixels interdependence. An adaptive network selection module controls the propagation routing path determining the optimal computational graph according to confidence-based criteria. We further propose a spatial adaptive attention network to avoid computational overhead in the transformer encoder, where the self-attention only aggregates the dependencies information among selected points. Our model achieves a harmonious proportion between accuracy and efficiency for dealing with varying scenarios, leading to notable advantages over static models with a fixed computational cost. Comprehensive experiments on aerial and prevalent tracking benchmarks achieve competitive results while operating at high speed, demonstrating its suitability on UAV-platforms which do not carry a dedicated GPU.

Original languageEnglish (US)
Title of host publication2022 International Conference on Unmanned Aircraft Systems, ICUAS 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages6
ISBN (Electronic)9781665405935
StatePublished - 2022
Event2022 International Conference on Unmanned Aircraft Systems, ICUAS 2022 - Dubrovnik, Croatia
Duration: Jun 21 2022Jun 24 2022

Publication series

Name2022 International Conference on Unmanned Aircraft Systems, ICUAS 2022


Conference2022 International Conference on Unmanned Aircraft Systems, ICUAS 2022

ASJC Scopus subject areas

  • Aerospace Engineering
  • Mechanical Engineering
  • Control and Optimization
  • Modeling and Simulation


Dive into the research topics of 'Siamese Adaptive Transformer Network for Real-Time Aerial Tracking'. Together they form a unique fingerprint.

Cite this