?
Weighted boxes fusion: Ensembling boxes from different object detection models
Image and Vision Computing. 2021. Vol. 107. P. 104117–0.
Соловьёв Р. А., Габрушева Т., Ванг В.
We present a novel method for combining predictions in ensembles of different object detection models: weighted boxes fusion. This method significantly improves the quality of the fused predicted rectangles for an ensemble.
We tested the method on several datasets and evaluated it in the context of the Open Images and COCO Object Detection challenges. It helped to achieve top results in these challenges. The source code is publicly available at GitHub.
Абрамов А. С., Chernyshev V. L., Mikhaylets E. et al., / Series Social Science Research Network "Social Science Research Network". 2025.
Computer vision is one of the most relevant modern research areas with broad practical applications. However, traditional solutions based on deep learning have signicant limitations and can be misleading. Topological data analysis, on the other hand, is a modern approach to solving similar problems using mathematically deterministic methods of algebraic topology that reduce the risk ...
Added: September 23, 2025
Rome: Springer, 2025.
This book constitutes the refereed proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2023, held in Rome, Italy, during November 13-15, 2023.
The 9 full papers and 8 short papers included in this book were carefully reviewed and selected from 166 submissions. They were organized in topical sections ...
Added: May 2, 2025
Alahmid M., Bhimani K. R., Saradva K. et al., , in: Select Proceedings of CHSN 2023. High Performance Computing, Smart Devices and NetworksVol. 1262: Lecture Notes in Electrical Engineering.: Singapore: Springer, 2024. P. 87–100.
To give shift in safety protocols, we have employed advanced deep learning algorithms and frameworks to construct an innovative AI model. The designed model detects the usage of personal protective equipment (PPE) by workers in high-risk industries such as construction and manufacturing. We have used Google’s TensorFlow object detection API to modify and train a model for ...
Added: January 17, 2025
Соловьёв Р. А., Габрушева Т., Калинин А., Computers in Biology and Medicine 2022 Vol. 141 P. 105–113
Adequate blood supply is critical for normal brain function. Brain vasculature dysfunctions, including stalled blood flow in cerebral capillaries, are associated with cognitive decline and pathogenesis in Alzheimer's disease. Recent advances in imaging technology enabled generation of high-quality 3D images that can be used to visualize stalled blood vessels. However, localization of stalled vessels in ...
Added: January 15, 2025
Белокопытов А. С., Kleeva D., Ossadtchi A., , in: Advances in Neural Computation, Machine Learning, and Cognitive Research VIII.: Springer, 2024. P. 317–326.
Added: October 23, 2024
Nikulin A. M., Belousov Y., Svidchenko O. et al., , in: Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track.: PMLR, 2022.
Reinforcement learning competitions advance the field by providing appropriate scope and support to develop solutions toward a specific problem. To promote the development of more broadly applicable methods, organizers need to enforce the use of general techniques, the use of sample-efficient methods, and the reproducibility of the results. While beneficial for the research community, these ...
Added: October 8, 2024
Hamplová A., Lyavdansky A., Novák T. et al., CMES - Computer Modeling in Engineering and Sciences 2024 Vol. 140 No. 3 P. 2869–2889
This study presents a single-class and multi-class instance segmentation approach applied to ancient Palmyrene inscriptions, employing two state-of-the-art deep learning algorithms, namely YOLOv8 and Roboflow 3.0. The goal is to contribute to the preservation and understanding of historical texts, showcasing the potential of modern deep learning methods in archaeological research. Our research culminates in several ...
Added: July 17, 2024
Gambashidze A., Dadukin A., Golyadkin M. et al., , in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.: IEEE, 2024. P. 15055–15064.
Added: July 15, 2024
Rogachev A., Ratnikov F., Computing and Software for Big Science 2024 Vol. 8 No. 1 Article 12
In this paper, we explore the use of Generative Adversarial Networks (GANs) to speed up the simulation process while ensuring that the generated results are consistent in terms of physics metrics. Our main focus is the application of spectral normalization for GANs to generate electromagnetic calorimeter (ECAL) response data, which is a crucial component of ...
Added: July 2, 2024
Menshchikov A., Shadrin D., Prutyanov V. et al., IEEE Transactions on Computers 2021 Vol. 70 No. 8 P. 1175–1188
The Hogweed of Sosnowskyi (lat. Heracleum sosnowskyi) is poisonous for humans, dangerous for farming crops, and local ecosystems. This plant is fast-growing and has already spread all over Eurasia: from Germany to the Siberian part of Russia, and its distribution expands year-by-year. In-situ detection of this harmful plant is a tremendous challenge for many countries. ...
Added: May 11, 2024
Cham: Springer, 2024.
This book constitutes revised selected papers from the thoroughly refereed proceedings of the 11th International Conference on Analysis of Images, Social Networks and Texts, AIST 2023, held in Yerevan, Armenia, during September 28-30, 2023.
The 24 full papers included in this book were carefully reviewed and selected from 93 submissions. They were organized in topical sections ...
Added: March 25, 2024
Nikita Starodubcev, Dmitry Baranchuk, Artem Fedorov et al., , in: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).: IEEE, 2024. P. 9275–9285.
Knowledge distillation methods have recently shown to be a promising direction to speedup the synthesis of large-scale diffusion models by requiring only a few inference steps. While several powerful distillation methods were recently proposed, the overall quality of student samples is typically lower compared to the teacher ones, which hinders their practical usage. In this ...
Added: March 5, 2024
IEEE, 2024.
Added: March 5, 2024
Nikita O. Starodubcev, Nikitin N., Andronova E. et al., Engineering Applications of Artificial Intelligence 2023 Vol. 119 Article 105715
In recent years generative design techniques have become firmly established in numerous applied fields, especially in engineering. These methods are crucial for automating the initial stages of the engineering design of various structures, which reduces the amount of routine work. However, existing approaches are limited by the specificity of the problem under consideration. In addition, ...
Added: March 5, 2024
Zagitov A., Chebotareva E., Toschev A. et al., Computer Optics 2024 Vol. 48 No. 2 P. 242–252
A computer vision based real-time object detection on low-power devices is economically attractive, yet a technically challenging task. The paper presents results of benchmarks on popular deep neural network models, which are often used for this task. The results of experiments provide insights into trade-offs between accuracy, speed, and computational efficiency of MobileNetV2 SSD, CenterNet ...
Added: February 25, 2024
Zhevnenko D., Kazantsev M., Makarov I., Journal of Industrial Information Integration 2023 Vol. 33 Article 100444
The paper deals with the problem of controlling the state of industrial devices according to the readings of their sensors. The current methods are based on an approach to feature extraction in which the prediction occurs. We propose an interaction method of multiple blocks of different complexity, which aggregate information differently over time, to create ...
Added: February 15, 2024
Kotelnikov A., Baranchuk D., Ivan Rubachev et al., , in: Proceedings of the 40th International Conference on Machine Learning: Volume 202: International Conference on Machine Learning, 23-29 July 2023, Honolulu, Hawaii, USAVol. 202: International Conference on Machine Learning, 23-29 July 2023, Honolulu, Hawaii, USA.: PMLR, 2023. P. 17564–17579.
Denoising diffusion probabilistic models are becoming the leading generative modeling paradigm for many important data modalities. Being the most prevalent in the computer vision community, diffusion models have recently gained some attention in other domains, including speech, NLP, and graph-like data. In this work, we investigate if the framework of diffusion models can be advantageous ...
Added: February 11, 2024