Szczegóły publikacji
Opis bibliograficzny
A new approach to descriptors generation for image retrieval by analyzing activations of deep neural network layers / Paweł Staszewski, Maciej Jaworski, Jinde Cao, Leszek RUTKOWSKI // IEEE Transactions on Neural Networks and Learning Systems ; ISSN 2162-237X. — 2022 — vol. 33 no. 12, s. 7913–7920. — Bibliogr. s. 7920, Abstr. — L. Rutkowski - dod. afiliacja: Systems Research Institute of the Polish Academy of Sciences, Warsaw, Poland
Autorzy (4)
- Staszewski Paweł
- Jaworski Maciej
- Cao Jinde
- AGHRutkowski Leszek
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 144556 |
|---|---|
| Data dodania do BaDAP | 2023-01-12 |
| Tekst źródłowy | URL |
| DOI | 10.1109/TNNLS.2021.3084633 |
| Rok publikacji | 2022 |
| Typ publikacji | artykuł w czasopiśmie |
| Otwarty dostęp |  |
| Czasopismo/seria | IEEE Transactions on Neural Networks and Learning Systems |
Abstract
In this brief, we consider the problem of descriptors construction for the task of content-based image retrieval using deep neural networks. The idea of neural codes, based on fully connected layers' activations, is extended by incorporating the information contained in convolutional layers. It is known that the total number of neurons in the convolutional part of the network is large and the majority of them have little influence on the final classification decision. Therefore, in this brief, we propose a novel algorithm that allows us to extract the most significant neuron activations and utilize this information to construct effective descriptors. The descriptors consisting of values taken from both the fully connected and convolutional layers perfectly represent the whole image content. The images retrieved using these descriptors match semantically very well to the query image, and also, they are similar in other secondary image characteristics, such as background, textures, or color distribution. These features of the proposed descriptors are verified experimentally based on the IMAGENET1M dataset using the VGG16 neural network. For comparison, we also test the proposed approach on the ResNet50 network.
