Academic Journal
Generating of synthetic datasets using diffusion models for solving computer vision tasks in urban applications.
| Τίτλος: | Generating of synthetic datasets using diffusion models for solving computer vision tasks in urban applications. |
|---|---|
| Συγγραφείς: | Reutov, Ilya1 (AUTHOR) dr.reutov98@mail.ru |
| Πηγή: | Procedia Computer Science. 2023, Vol. 229, p335-344. 10p. |
| Θεματικοί όροι: | Computer vision, Artificial neural networks, Object recognition (Computer vision), Neural computers, Computer simulation, Deep learning, Intelligent transportation systems |
| People: | Kandinsky, Wassily, 1866-1944 |
| Περίληψη: | The paper illustrates the process of generating synthetic data using diffusion neural networks for solving popular computer vision tasks in urban applications: traffic vehicles detection and classification. The result of this study demonstrated new approach for synthetic datasets creation using modern generative neural networks. To elaborate this approach, experiments were performed to generate synthetic dataset to solve the above basic computer vision problem in urban applications using the most advanced diffusion neural network models (Kandinsky 2.2). Experiments were performed on these datasets to train deep neural networks to solve the object detection problem (YOLOv5). The results of testing the trained detectors on a specially selected validation dataset showed the potential viability of a synthetic dataset generation approach using diffusion neural network models. However, full-fledged use of this approach to generate synthetic datasets that can be used in training deep neural networks of computer vision in production is accompanied by some difficulties, namely high difference between domains of real data and generated data, high labor costs of tuning trained diffusion models to achieve the highest quality of generation, etc. [ABSTRACT FROM AUTHOR] |
| Βάση Δεδομένων: | Supplemental Index |
| FullText | Links: – Type: other Text: Availability: 0 CustomLinks: – Url: https://www.doi.org/10.1016/j.procs.2023.12.036? Name: ScienceDirect (all content) (s7799221) Category: fullText Text: View record from ScienceDirect MouseOverText: View record from ScienceDirect |
|---|---|
| Header | DbId: edo DbLabel: Supplemental Index An: 174470568 RelevancyScore: 938 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 937.867004394531 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Generating of synthetic datasets using diffusion models for solving computer vision tasks in urban applications. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Reutov%2C+Ilya%22">Reutov, Ilya</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> dr.reutov98@mail.ru</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Procedia+Computer+Science%22">Procedia Computer Science</searchLink>. 2023, Vol. 229, p335-344. 10p. – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Computer+vision%22">Computer vision</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Object+recognition+%28Computer+vision%29%22">Object recognition (Computer vision)</searchLink><br /><searchLink fieldCode="DE" term="%22Neural+computers%22">Neural computers</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+simulation%22">Computer simulation</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Intelligent+transportation+systems%22">Intelligent transportation systems</searchLink> – Name: SubjectPerson Label: People Group: Su Data: <searchLink fieldCode="PE" term="%22Kandinsky%2C+Wassily%2C+1866-1944%22">Kandinsky, Wassily, 1866-1944</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: The paper illustrates the process of generating synthetic data using diffusion neural networks for solving popular computer vision tasks in urban applications: traffic vehicles detection and classification. The result of this study demonstrated new approach for synthetic datasets creation using modern generative neural networks. To elaborate this approach, experiments were performed to generate synthetic dataset to solve the above basic computer vision problem in urban applications using the most advanced diffusion neural network models (Kandinsky 2.2). Experiments were performed on these datasets to train deep neural networks to solve the object detection problem (YOLOv5). The results of testing the trained detectors on a specially selected validation dataset showed the potential viability of a synthetic dataset generation approach using diffusion neural network models. However, full-fledged use of this approach to generate synthetic datasets that can be used in training deep neural networks of computer vision in production is accompanied by some difficulties, namely high difference between domains of real data and generated data, high labor costs of tuning trained diffusion models to achieve the highest quality of generation, etc. [ABSTRACT FROM AUTHOR] |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edo&AN=174470568 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1016/j.procs.2023.12.036 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 10 StartPage: 335 Subjects: – SubjectFull: Kandinsky, Wassily, 1866-1944 Type: general – SubjectFull: Computer vision Type: general – SubjectFull: Artificial neural networks Type: general – SubjectFull: Object recognition (Computer vision) Type: general – SubjectFull: Neural computers Type: general – SubjectFull: Computer simulation Type: general – SubjectFull: Deep learning Type: general – SubjectFull: Intelligent transportation systems Type: general Titles: – TitleFull: Generating of synthetic datasets using diffusion models for solving computer vision tasks in urban applications. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Reutov, Ilya IsPartOfRelationships: – BibEntity: Dates: – D: 15 M: 07 Text: 2023 Type: published Y: 2023 Identifiers: – Type: issn-print Value: 18770509 Numbering: – Type: volume Value: 229 Titles: – TitleFull: Procedia Computer Science Type: main |
| ResultId | 1 |