Unsupervised Construction of Task-Specific Datasets for Object Re-identification

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21240%2F21%3A00350725" target="_blank" >RIV/68407700:21240/21:00350725 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/67985807:_____/21:00548651

Výsledek na webu

<a href="https://doi.org/10.1145/3477911.3477922" target="_blank" >https://doi.org/10.1145/3477911.3477922</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3477911.3477922" target="_blank" >10.1145/3477911.3477922</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Unsupervised Construction of Task-Specific Datasets for Object Re-identification

Popis výsledku v původním jazyce

In the last decade, we have seen a significant uprise of deep neural networks in image processing tasks and many other research areas. However, while various neural architectures have successfully solved numerous tasks, they constantly demand more and more processing time and training data. Moreover, the current trend of using existing pre-trained architectures just as backbones and attaching new processing branches on top not only increases this demand but diminishes the explainability of the whole model. Our research focuses on combinations of explainable building blocks for the image processing tasks, such as object tracking. We propose a combination of Mask R-CNN, state-of-the-art object detection and segmentation neural network, with our previously published method of sparse feature tracking. Such a combination allows us to track objects by connecting detected masks using the proposed sparse feature tracklets. However, this method cannot recover from complete object occlusions and has to be assisted by an object re-identification. To this end, this paper uses our feature tracking method for a slightly different task: an unsupervised extraction of object representations that we can directly use to fine-tune an object re-identification algorithm. As we have to use objects masks already in the object tracking, our approach utilises the additional information as an alpha channel of the object representations, which further increases the precision of the re-identification. An additional benefit is that our fine-tuning method can be employed even in a fully online scenario.

Název v anglickém jazyce

Unsupervised Construction of Task-Specific Datasets for Object Re-identification

Popis výsledku anglicky

In the last decade, we have seen a significant uprise of deep neural networks in image processing tasks and many other research areas. However, while various neural architectures have successfully solved numerous tasks, they constantly demand more and more processing time and training data. Moreover, the current trend of using existing pre-trained architectures just as backbones and attaching new processing branches on top not only increases this demand but diminishes the explainability of the whole model. Our research focuses on combinations of explainable building blocks for the image processing tasks, such as object tracking. We propose a combination of Mask R-CNN, state-of-the-art object detection and segmentation neural network, with our previously published method of sparse feature tracking. Such a combination allows us to track objects by connecting detected masks using the proposed sparse feature tracklets. However, this method cannot recover from complete object occlusions and has to be assisted by an object re-identification. To this end, this paper uses our feature tracking method for a slightly different task: an unsupervised extraction of object representations that we can directly use to fine-tune an object re-identification algorithm. As we have to use objects masks already in the object tracking, our approach utilises the additional information as an alpha channel of the object representations, which further increases the precision of the re-identification. An additional benefit is that our fine-tuning method can be employed even in a fully online scenario.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA18-18080S" target="_blank" >GA18-18080S: Objevování znalostí v datech o aktivitě člověka založené na fúzi</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

ICCTA 2021 Conference Proceedings

ISBN

978-1-4503-9052-1

ISSN

—

e-ISSN

—

Počet stran výsledku

7

Strana od-do

66-72

Název nakladatele

Association for Computing Machinery

Místo vydání

New York

Místo konání akce

Vídeň

Datum konání akce

13. 7. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—