Method of Controlled Image Degradation for Detecting Attention Centers in Classification Neural Networks
| dc.contributor.author | Dorenskyi О. | |
| dc.contributor.author | Drieiev О. | |
| dc.contributor.author | Drieievа Н. | |
| dc.contributor.author | Доренський O. П. | |
| dc.contributor.author | Дрєєв О. М. | |
| dc.contributor.author | Дрєєва Г. М. | |
| dc.date.accessioned | 2026-05-25T07:35:36Z | |
| dc.date.issued | 2026 | |
| dc.description.abstract | The paper discusses a method of controlled image degradation for detecting attention centers in neural networks for classification tasks. A method is proposed that preserves classification logits during image degradation, using a uniform background and optimizing the ‘transparency’ map. This approach allows working with modern neural network architectures such as MIXER and ViT and improves training by identifying significant elements for classification. | |
| dc.identifier.citation | Dorenskyi O., Drieiev O., Drieieva H. Method of Controlled Image Degradation for Detecting Attention Centers in Classification Neural Networks // MINTECH 2026. Modern Information Technologies: From Theory to Practice : 1st International Sclentific and Practical Conference : book of abstracts, 22–23 May 2026. Lutsk : LNTU, 2026. P. 883-886. | |
| dc.identifier.uri | https://dspace.kntu.kr.ua/handle/123456789/19471 | |
| dc.language.iso | en | |
| dc.publisher | ЛНТУ | |
| dc.subject | computer vision | |
| dc.subject | attention localization | |
| dc.subject | data quality | |
| dc.title | Method of Controlled Image Degradation for Detecting Attention Centers in Classification Neural Networks | |
| dc.type | Thesis |