Robust discriminative tracking via query-by-bagging

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

Ishii

2018

Self Cite

Ensemble discriminative tracking utilizes a committee of classifiers, to label data samples, which are in turn, used for retraining the tracker to localize the target using the collective knowledge of the committee. Committee members could vary in their features, memory update schemes, or training data, however, it is inevitable to have committee members that excessively agree because of large overlaps in their version space. To remove this redundancy and have an effective ensemble learning, it is critical for the committee to include consistent hypotheses that differ from one-another, covering the version space with minimum overlaps. In this study, we propose an online ensemble tracker that directly generates a diverse committee by generating an efficient set of artificial training. The artificial data is sampled from the empirical distribution of the samples taken from both target and background, whereas the process is governed by query-by-committee to shrink the overlap between classifiers. The experimental results demonstrate that the proposed scheme outperforms conventional ensemble trackers on public benchmarks.

Section: Prior Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Efficient Diverse Ensemble for Discriminative Co-tracking

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

Ishii

2018

Self Cite

“…In supervised learning schemes (e.g., [28]), these thresholds are equal (τ l = τ u ), whereas by employing semisupervised learning for the classifier (e.g., [21], [41]), the trackers allow for some samples to be unlabeled. In addition, trackers based on multi-instance learning (e.g., [18], [34]), bag the samples and apply a label on each bag to handle ambiguity of labeling, and active-learning trackers (e.g., [42]) rely on their oracle for disambiguation. Finally, the target location y t is obtained by comparing the samples classification scores.…”

Section: A Tracking By Detectionmentioning

confidence: 99%

Efficient Version-Space Reduction for Visual Tracking

2017 14th Conference on Computer and Robot Vision (CRV)

Ishii

2017

Self Cite

Discrminative trackers, employ a classification approach to separate the target from its background. To cope with variations of the target shape and appearance, the classifier is updated online with different samples of the target and the background. Sample selection, labeling and updating the classifier is prone to various sources of errors that drift the tracker. We introduce the use of an efficient version space shrinking strategy to reduce the labeling errors and enhance its sampling strategy by measuring the uncertainty of the tracker about the samples. The proposed tracker, utilize an ensemble of classifiers that represents different hypotheses about the target, diversify them using boosting to provide a larger and more consistent coverage of the version-space and tune the classifiers' weights in voting. The proposed system adjusts the model update rate by promoting the co-training of the short-memory ensemble with a long-memory oracle. The proposed tracker outperformed state-of-the-art trackers on different sequences bearing various tracking challenges.

“…An alternative way to tune the weights of the weights of an ensemble is via a Bayesian treatment [6]. Aside from using different features, the members of an ensemble may be constructed from randomized subsets of training data [32] or different time snapshots of a classifier evolving by time [48].…”

Section: Related Workmentioning

confidence: 99%

“…where the weights α (c) t ∈ A t are tuned using boosting [3,16,32] or Bayesian treatment [5]. A larger weight implies that the corresponding classifier of th eensemble is more discriminative, hence more useful.…”

Section: Ensemble Discriminative Trackingmentioning

confidence: 99%

Active collaborative ensemble tracking

Mirzaei

2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)

et al. 2017

Self Cite

A discriminative ensemble tracker employs multiple classifiers, each of which casts a vote on all of the obtained samples. The votes are then aggregated in an attempt to localize the target object. Such method relies on collective competence and the diversity of the ensemble to approach the target/non-target classification task from different views. However, by updating all of the ensemble using a shared set of samples and their final labels, such diversity is lost or reduced to the diversity provided by the underlying features or internal classifiers' dynamics. Additionally, the classifiers do not exchange information with each other while striving to serve the collective goal, i.e., better classification. In this study, we propose an active collaborative information exchange scheme for ensemble tracking. This, not only orchestrates different classifier towards a common goal but also provides an intelligent update mechanism to keep the diversity of classifiers and to mitigate the shortcomings of one with the others. The data exchange is optimized with regard to an ensemble uncertainty utility function, and the ensemble is updated via co-training. The evaluations demonstrate promising results realized by the proposed algorithm for the real-world online tracking.