en
Назад
DOI: 10.17586/1023-5086-2020-87-08-52-57
УДК: 004.272 004.032.26
Применение метода экземплярной нормализации в моделях на основе глубокого обучения для задачи повторной идентификации
Полный текст «Оптического журнала»
Полный текст на elibrary.ru
Публикация в Journal of Optical Technology
Ященко А.В., Родионов С.А., Потапов А.С. Применение метода экземплярной нормализации в моделях на основе глубокого обучения для задачи повторной идентификации // Оптический журнал. 2020. Т. 87. № 8. С. 52–57. http://doi.org/10.17586/1023-5086-2020-87-08-52-57
Yashchenko A.V., Rodionov S.A., Potapov A.S. Method of instance normalization in deep-learning-based models for re-identification [in Russian] // Opticheskii Zhurnal. 2020. V. 87. № 8. P. 52–57. http://doi.org/10.17586/1023-5086-2020-87-08-52-57
A. V. Yashchenko, S. A. Rodionov, and A. S. Potapov, "Method of instance normalization in deep-learning-based models for re-identification," Journal of Optical Technology. 87(8), 487-490 (2020). https://doi.org/10.1364/JOT.87.000487
В данной работе исследованы модели для решения задачи повторной идентификации пешеходов на основе глубокого обучения. Рассмотренные модели используют только изображения пешеходов, не требуя дополнительной пространственно-временнóй информации, которая в разных случаях может различаться. Предлагается модификация исследованных моделей на основе нормализации карт признаков. Представлены результаты оценки качества моделей, демонстрирующие улучшение, в лучшем случае на 10%, относительно результатов моделей без применения предложенной модификации.
глубокое обучение, повторная идентификация пешеходов
Коды OCIS: 150.1135, 100.4996
Список источников:1. Poongothai E., Suruliandi A. Survey on colour, texture and shape feature analysis for person re-identification technique // Advances in Vision Computing: An International Journal (AVC). 2016. V. 3. № 3. doi: 10.5121/avc.2016.3303
2. Jaderberg M., Simonyan K., Zisserman A. Spatial transformer networks // Advances in Neural Information Processing Systems. 2015. V. 28. P. 2017–2025.
3. Potapov A., Shcherbakov O., Zhdanov I. HyperNets and their application to learning spatial transformations // 27th International Conference on Artificial Neural Networks. Rhodes, Greece. October 4–7, 2018. P. 476–486.
4. Sabour S., Frosst N., Hinton G.E. Dynamic routing between capsules // Advances in Neural Information Processing Systems. 2017. V. 30. P. 3856–3866.
5. Hermans A., Beyer L. In defense of the triplet loss for person re-identification [электронный ресурс] 2017. — Режим доступа: https://arxiv.org/abs/1703.07737, свободный.
6. Zhang F. View confusion feature learning for person re-identification // The IEEE International Conference on Computer Vision (ICCV). Seoul, Korea. October 27 – November 2, 2019. P. 6639–6648.
7. Luo H., Gu Y. Bag of tricks and a strong baseline for deep person re-identification [электронный ресурс] 2019. — Режим доступа: https://arxiv.org/abs/1903.07071, свободный.
8. Potapov A., Rodionov S., Latapie H. Metric embedding autoencoders for unsupervised cross-dataset transfer learning [электронный ресурс] 2018. — Режим доступа: https://arxiv.org/abs/1807.10591, свободный.
9. Rodionov S., Potapov A., Latapie H. Improving deep models of person re-identification for cross-dataset usage // Artificial Intelligence Applications and Innovations. 2018. P. 75–84. doi: 10.1007/978-3-319-92007-8_7
10. Zhong Z., Zheng L. Invariance matters: exemplar memory for domain adaptive person re-identification // Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, CA, USA. June 16–20. 2019. P. 598–607.
11. Wei L., Zhang S. Person transfer GAN to bridge domain gap for person re-identification // Conference on Computer Vision and Pattern Recognition (CVPR). Salt Lake City, Utah, USA. June 18–22. 2018. С. 79–88.
12. Ulyanov D., Vedaldi A. Instance normalization: The missing ingredient for fast stylization [электронный ресурс] 2016. — Режим доступа: https://arxiv.org/abs/1607.08022, свободный.
13. Zheng Z., Yang X. Joint discriminative and generative learning for person re-identification // Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, CA, USA. June 16–20. 2019. P. 2138–2147.
14. Zhong Z., Zheng L. Camera style adaptation for person re-identification // Conference on Computer Vision and Pattern Recognition (CVPR). Salt Lake City, Utah, USA. June 18–22. 2018. P. 5157–5166.
15. Jia J., Ruan Q. Frustratingly easy person re-identification: generalizing person re-ID in practice // 30th British Machine Vision Conference. Cardiff, UK. September 9–12, 2019. P. 117–131.
16. He K., Zhang X. Deep residual learning for image recognition // Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, Nevada, USA. June 26 –July 1. 2016. P. 770–778.
17. Ioffe S., Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift // International Conference on Machine Learning. Lille, France. July 7–9, 2015. P. 448–456.
18. Deng J., Dong W. ImageNet: A large-scale hierarchical image database // IEEE Conference on Computer Vision and Pattern Recognition. Miami Beach, FL, USA. June 20–21, 2009. P. 248–255.
19. Li W., Zhao R. DeepReID: Deep filter pairing neural network for person re-identification // IEEE Conference on Computer Vision and Pattern Recognition. Columbus. Ohio, USA. June 24–27. 2014. P. 152–159.
20. Bak S., Carr P. Domain adaptation through synthesis for unsupervised person re-identification // Computer Vision — ECCV. 2018. P. 193–209.
21. Zheng L., Shen L. Scalable person re-identification: A benchmark // IEEE International Conference on Computer Vision (ICCV). Santiago, Chile. 2015. P. 1116–1124.
22. Ristani E., Solera F., Zou F. Performance measures and a data set for multi-target, multi-camera tracking [электронный ресурс] 2016. — Режим доступа: https://users.cs.duke.edu/~tomasi/papers/ristani/ristaniBmtt16.pdf, свободный.
23. Wu A., Zheng W.-S., Yu H.-X., Shaogang Gong, Jianhuang Lai. RGB-infrared cross-modality person re-identification // IEEE International Conference on Computer Vision. Venice, Italy. October 22–29, 2017. P. 5390–5399. 24. Gray D., Brennan S. Evaluating appearance models for recognition, reacquisition, and tracking // IEEE International Workshop on Performance Evaluation for Tracking and Surveillance. Rio de Janeiro, Brazil. October 14, 2007. V. 3. № 5. P. 1–7.