Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking.

@article{Gao2022RecursiveLE,
  title={Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking.},
  author={Jin Gao and Yan Lu and Xiaojuan Qi and Yutong Kou and Bing Li and Liang Li and Shan Yu and Weiming Hu},
  journal={IEEE transactions on pattern analysis and machine intelligence},
  year={2022},
  volume={PP}
}
  • Jin GaoYan Lu Weiming Hu
  • Published 28 December 2021
  • Computer Science
  • IEEE transactions on pattern analysis and machine intelligence
Tracking visual objects from a single initial exemplar in the testing phase has been broadly cast as a one-/few-shot problem, i.e., one-shot learning for initial adaptation and few-shot learning for online adaptation. The recent few-shot online adaptation methods incorporate the prior knowledge from large amounts of annotated training data via complex meta-learning optimization in the offline phase. This helps the online deep trackers to achieve fast adaptation and reduce overfitting risk in… 

Figures and Tables from this paper

Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking

  • Jin GaoWeiming HuYan Lu
  • Computer Science
    2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
This paper realizes this recursive LSE-aided online learning technique in the state-of-the-art RT-MDNet tracker, and the consistent improvements on four challenging benchmarks prove its efficiency without additional offline training and too much tedious work on parameter adjusting.

References

SHOWING 1-10 OF 114 REFERENCES

Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking

  • Jin GaoWeiming HuYan Lu
  • Computer Science
    2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
This paper realizes this recursive LSE-aided online learning technique in the state-of-the-art RT-MDNet tracker, and the consistent improvements on four challenging benchmarks prove its efficiency without additional offline training and too much tedious work on parameter adjusting.

Meta-Tracker: Fast and Robust Online Adaptation for Visual Object Trackers

This paper improves state-of-the-art visual object trackers that use online adaptation by using an offline meta-learning-based method to adjust the initial deep networks used in online adaptation-based tracking.

Incremental Learning for Robust Visual Tracking

A tracking method that incrementally learns a low-dimensional subspace representation, efficiently adapting online to changes in the appearance of the target, and includes a method for correctly updating the sample mean and a forgetting factor to ensure less modeling power is expended fitting older observations.

Real-Time Object Tracking via Meta-Learning: Efficient Model Adaptation and One-Shot Channel Pruning

A novel meta-learning framework for real-time object tracking with efficient model adaptation and channel pruning that greatly improves tracking performance by accelerating the convergence of online learning and reducing the cost of feature computation.

Deep Meta Learning for Real-Time Target-Aware Visual Tracking

A novel on-line visual tracking framework based on the Siamese matching network and meta-learner network that performs at a real-time speed while maintaining competitive performance among other state-of-the-art tracking algorithms.

Learning Discriminative Model Prediction for Tracking

An end-to-end tracking architecture, capable of fully exploiting both target and background appearance information for target model prediction, derived from a discriminative learning loss by designing a dedicated optimization process that is capable of predicting a powerful model in only a few iterations.

Visual Tracking via Dynamic Memory Networks

A dynamic memory network to adapt the template to the target's appearance variations during tracking and design a “negative” memory unit that stores templates for distractors, which are used to cancel out wrong responses from the object template.

Learning feed-forward one-shot learners

This paper constructs the learner as a second deep network, called a learnet, which predicts the parameters of a pupil network from a single exemplar, and obtains an efficient feed-forward one-shot learner, trained end-to-end by minimizing a one- shot classification objective in a learning to learn formulation.

Robust Object Tracking with Online Multiple Instance Learning

It is shown that using Multiple Instance Learning (MIL) instead of traditional supervised learning avoids these problems and can therefore lead to a more robust tracker with fewer parameter tweaks.

Struck: Structured Output Tracking with Kernels

A framework for adaptive visual object tracking based on structured output prediction that is able to outperform state-of-the-art trackers on various benchmark videos and can easily incorporate additional features and kernels into the framework, which results in increased tracking performance.
...