Dynamical hyperparameter optimization via deep reinforcement learning in tracking

Xingping Dong, Jianbing Shen*, Wenguan Wang, Ling Shao, Haibin Ling, Fatih Porikli

*Corresponding author for this work

    Research output: Contribution to journalArticlepeer-review

    141 Citations (Scopus)

    Abstract

    Hyperparameters are numerical pre-sets whose values are assigned prior to the commencement of a learning process. Selecting appropriate hyperparameters is often critical for achieving satisfactory performance in many vision problems, such as deep learning-based visual object tracking. However, it is often difficult to determine their optimal values, especially if they are specific to each video input. Most hyperparameter optimization algorithms tend to search a generic range and are imposed blindly on all sequences. In this paper, we propose a novel dynamical hyperparameter optimization method that adaptively optimizes hyperparameters for a given sequence using an action-prediction network leveraged on continuous deep Q-learning. Since the observation space for object tracking is significantly more complex than those in traditional control problems, existing continuous deep Q-learning algorithms cannot be directly applied. To overcome this challenge, we introduce an efficient heuristic strategy to handle high dimensional state space, while also accelerating the convergence behavior. The proposed algorithm is applied to improve two representative trackers, a Siamese-based one and a correlation-filter-based one, to evaluate its generalizability. Their superior performances on several popular benchmarks are clearly demonstrated. Our source code is available at https://github.com/shenjianbing/dqltracking.

    Original languageEnglish
    Article number8918068
    Pages (from-to)1515-1529
    Number of pages15
    JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
    Volume43
    Issue number5
    DOIs
    Publication statusPublished - 1 May 2021

    Fingerprint

    Dive into the research topics of 'Dynamical hyperparameter optimization via deep reinforcement learning in tracking'. Together they form a unique fingerprint.

    Cite this