2021
DOI: 10.48550/arxiv.2103.10130
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Real-Time Visual Object Tracking via Few-Shot Learning

Jinghao Zhou,
Bo Li,
Peng Wang
et al.

Abstract: Visual Object Tracking (VOT) can be seen as an extended task of Few-Shot Learning (FSL). While the concept of FSL is not new in tracking and has been previously applied by prior works, most of them are tailored to fit specific types of FSL algorithms and may sacrifice running speed. In this work, we propose a generalized two-stage framework that is capable of employing a large variety of FSL algorithms while presenting faster adaptation speed. The first stage uses a Siamese Regional Proposal Network to efficie… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
1
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
1
1

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(2 citation statements)
references
References 38 publications
0
1
0
Order By: Relevance
“…We note that there are many works which apply "trivial" CI methods (see "Common non-LSL approaches to CI" section) independent of the rest of the model, and thus are not included in the body of this survey nor in Table 1. These measures include loss functions such as focal loss [17][18][19][20][21], class-weighted loss [22][23][24][25], difficulty-weighted loss [19,26], and others [27][28][29][30][31][32]; as well as resampling methods such as random undersampling [33], difficulty-based sampling [34], and other forms of balancing sampling [22,35,36] (citations above are not exhaustive). In addition to the works above, we note but do not include a paper by Li et al which proposes a novel few-shot intent-detection benchmark which contains various forms of class imbalance, but does not propose measures to explicitly counter this imbalance [37].…”
Section: Solving Imbalance Within Lslmentioning
confidence: 99%
“…We note that there are many works which apply "trivial" CI methods (see "Common non-LSL approaches to CI" section) independent of the rest of the model, and thus are not included in the body of this survey nor in Table 1. These measures include loss functions such as focal loss [17][18][19][20][21], class-weighted loss [22][23][24][25], difficulty-weighted loss [19,26], and others [27][28][29][30][31][32]; as well as resampling methods such as random undersampling [33], difficulty-based sampling [34], and other forms of balancing sampling [22,35,36] (citations above are not exhaustive). In addition to the works above, we note but do not include a paper by Li et al which proposes a novel few-shot intent-detection benchmark which contains various forms of class imbalance, but does not propose measures to explicitly counter this imbalance [37].…”
Section: Solving Imbalance Within Lslmentioning
confidence: 99%
“…This task closely resembles the FSL task setting, which involves classification using minimal data. Consequently, some researchers [137] have applied FSL to object tracking. However, domain gaps frequently exist between auxiliary data and target data due to variations in devices and data acquisition methods.…”
Section: Applicationsmentioning
confidence: 99%