Deep regression trackers are among the fastest tracking algorithms available, and therefore suitable for real-time robotic applications. However, their accuracy is inadequate in many domains due to distribution shift and overfitting. In this paper we overcome such limitations by presenting the first methodology for domain adaption of such a class of trackers. To reduce the labeling effort we propose a weakly-supervised adaptation strategy, in which reinforcement learning is used to express weak supervision as a scalar application-dependent and temporally-delayed feedback. At the same time, knowledge distillation is employed to guarantee learning stability and to compress and transfer knowledge from more powerful but slower trackers. Extensive experiments on five different domains demonstrate the relevance of our methodology. Real-time speed is achieved on embedded devices and on machines without GPUs, while accuracy reaches significant results.
Weakly-Supervised Domain Adaptation of Deep Regression Trackers via Reinforced Knowledge Distillation
Dunnhofer M.;Martinel N.;Micheloni C.
2021-01-01
Abstract
Deep regression trackers are among the fastest tracking algorithms available, and therefore suitable for real-time robotic applications. However, their accuracy is inadequate in many domains due to distribution shift and overfitting. In this paper we overcome such limitations by presenting the first methodology for domain adaption of such a class of trackers. To reduce the labeling effort we propose a weakly-supervised adaptation strategy, in which reinforcement learning is used to express weak supervision as a scalar application-dependent and temporally-delayed feedback. At the same time, knowledge distillation is employed to guarantee learning stability and to compress and transfer knowledge from more powerful but slower trackers. Extensive experiments on five different domains demonstrate the relevance of our methodology. Real-time speed is achieved on embedded devices and on machines without GPUs, while accuracy reaches significant results.File | Dimensione | Formato | |
---|---|---|---|
RA-L-IEEE.pdf
non disponibili
Tipologia:
Documento in Pre-print
Licenza:
Non pubblico
Dimensione
2.46 MB
Formato
Adobe PDF
|
2.46 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.