Semi-supervised Learning in Camera Surveillance Image Classification

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F21%3A00356755" target="_blank" >RIV/68407700:21730/21:00356755 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/ICCP53602.2021.9733483" target="_blank" >https://doi.org/10.1109/ICCP53602.2021.9733483</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICCP53602.2021.9733483" target="_blank" >10.1109/ICCP53602.2021.9733483</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Semi-supervised Learning in Camera Surveillance Image Classification

Popis výsledku v původním jazyce

Recognizing pedestrian attributes in camera surveillance images is a very hard problem, due to the lack of high-quality labeled data. In the field of deep learning the semi-supervised learning paradigm provides a possible answer to this problem. We propose a novel semi-supervised model that we call Binary Mean Teacher, tailored for binary classification task of detecting the presence of wearable objects. We train our model in a traditional scenario with a randomly initialized model, but we also explore fine-tuning a model pretrained on a large-scale image dataset. The performance of our model is compared to strong supervised baselines trained or fine-tuned using our dataset and the same augmentation strategy as in our model. We evaluate the impact of various augmentation strategies commonly used in deep learning on the performance of models in our binary classification task. Using only 1000 labeled training images, randomly initialized Binary Mean Teacher model achieves roughly 90% classification accuracy compared to 75% accuracy of randomly initialized supervised model that does not use any augmentations. When both Binary Mean Teacher and the supervised model are pretrained using the ImageNet dataset, and augmentations are used for both models, the Binary Mean Teacher achieves 92% accuracy compared to 90% accuracy of the supervised model.

Název v anglickém jazyce

Semi-supervised Learning in Camera Surveillance Image Classification

Popis výsledku anglicky

Recognizing pedestrian attributes in camera surveillance images is a very hard problem, due to the lack of high-quality labeled data. In the field of deep learning the semi-supervised learning paradigm provides a possible answer to this problem. We propose a novel semi-supervised model that we call Binary Mean Teacher, tailored for binary classification task of detecting the presence of wearable objects. We train our model in a traditional scenario with a randomly initialized model, but we also explore fine-tuning a model pretrained on a large-scale image dataset. The performance of our model is compared to strong supervised baselines trained or fine-tuned using our dataset and the same augmentation strategy as in our model. We evaluate the impact of various augmentation strategies commonly used in deep learning on the performance of models in our binary classification task. Using only 1000 labeled training images, randomly initialized Binary Mean Teacher model achieves roughly 90% classification accuracy compared to 75% accuracy of randomly initialized supervised model that does not use any augmentations. When both Binary Mean Teacher and the supervised model are pretrained using the ImageNet dataset, and augmentations are used for both models, the Binary Mean Teacher achieves 92% accuracy compared to 90% accuracy of the supervised model.

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

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

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

2021 IEEE 17th International Conference on Intelligent Computer Communication and Processing (ICCP)

ISBN

978-1-6654-0976-6

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

155-162

Název nakladatele

IEEE Industrial Electronic Society

Místo vydání

Vienna

Místo konání akce

Cluj-Napoca

Datum konání akce

28. 10. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—