Sökning: WFRF:(Dong Xingping)
> (2022) >
Distilled Siamese N...
Distilled Siamese Networks for Visual Tracking
-
- Shen, Jianbing (författare)
- Univ Macau, Peoples R China
-
- Liu, Yuanpei (författare)
- Beijing Inst Technol, Peoples R China
-
- Dong, Xingping (författare)
- Incept Inst Artificial Intelligence, U Arab Emirates
-
visa fler...
-
- Lu, Xiankai (författare)
- Shandong Univ, Peoples R China
-
- Khan, Fahad (författare)
- Linköpings universitet,Datorseende,Tekniska fakulteten,Incept Inst Artificial Intelligence, U Arab Emirates
-
- Hoi, Steven (författare)
- Singapore Management Univ, Singapore; Salesforce Res Asia, Singapore
-
visa färre...
-
(creator_code:org_t)
- IEEE COMPUTER SOC, 2022
- 2022
- Engelska.
-
Ingår i: IEEE Transactions on Pattern Analysis and Machine Intelligence. - : IEEE COMPUTER SOC. - 0162-8828 .- 1939-3539. ; 44:12, s. 8896-8909
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- In recent years, Siamese network based trackers have significantly advanced the state-of-the-art in real-time tracking. Despite their success, Siamese trackers tend to suffer from high memory costs, which restrict their applicability to mobile devices with tight memory budgets. To address this issue, we propose a distilled Siamese tracking framework to learn small, fast and accurate trackers (students), which capture critical knowledge from large Siamese trackers (teachers) by a teacher-students knowledge distillation model. This model is intuitively inspired by the one teacher versus multiple students learning method typically employed in schools. In particular, our model contains a single teacher-student distillation module and a student-student knowledge sharing mechanism. The former is designed using a tracking-specific distillation strategy to transfer knowledge from a teacher to students. The latter is utilized for mutual learning between students to enable in-depth knowledge understanding. Extensive empirical evaluations on several popular Siamese trackers demonstrate the generality and effectiveness of our framework. Moreover, the results on five tracking benchmarks show that the proposed distilled trackers achieve compression rates of up to 18x and frame-rates of 265 FPS, while obtaining comparable tracking accuracy compared to base models.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- Training; Target tracking; Real-time systems; Visualization; Correlation; Knowledge engineering; Feature extraction; Siamese network; teacher-students; knowledge distillation; visual object tracking; siamese trackers
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas