{"id":9720,"date":"2023-10-08T13:54:56","date_gmt":"2023-10-08T13:54:56","guid":{"rendered":"https:\/\/new.evorain.pl\/nowe-podejscie-do-generowania-deskryptorow-do-wyszukiwania-obrazow-poprzez-analize-aktywacji-warstw-glebokiej-sieci-neuronowej\/"},"modified":"2024-11-08T12:31:33","modified_gmt":"2024-11-08T12:31:33","slug":"nowe-podejscie-do-generowania-deskryptorow-do-wyszukiwania-obrazow-poprzez-analize-aktywacji-warstw-glebokiej-sieci-neuronowej","status":"publish","type":"post","link":"https:\/\/evorain.com\/pl\/nowe-podejscie-do-generowania-deskryptorow-do-wyszukiwania-obrazow-poprzez-analize-aktywacji-warstw-glebokiej-sieci-neuronowej\/","title":{"rendered":"Nowe podej\u015bcie do generowania deskryptor\u00f3w do wyszukiwania obraz\u00f3w poprzez analiz\u0119 aktywacji warstw g\u0142\u0119bokiej sieci neuronowej"},"content":{"rendered":"\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t

\n\t\t\t\t\t\tAutorzy\n\t\t\t\t\t<\/h2>

Szczeg\u00f3\u0142y publikacji<\/h3><\/div><\/div>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t
\t\t\t\t
\n\t\t\t\t\t

Pawe\u0142 Staszewski, Maciej Jaworski, Jinde Cao, Leszek Rutkowski: <\/span> A New Approach to Descriptors Generation for Image Retrieval by Analyzing Activations of Deep Neural Network Layers<\/span>. In: <\/span>IEEE Transactions on Neural Networks and Learning Systems, <\/span>vol. 33, <\/span>no. 12, <\/span>pp. 7913-7920, <\/span>2022<\/span>.<\/span><\/div><\/p>\n\t\t\t\t<\/div>\n\t\t\t<\/div><\/div>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t

\n\t\t\t\t\t\tStreszczenie\n\t\t\t\t\t<\/h2>

Streszczenie publikacji<\/h3><\/div><\/div>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t
\t\t\t\t
\n\t\t\t\t\t

Abstract<\/h2>

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\u2019 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.<\/p><\/p>\n\t\t\t\t<\/div>\n\t\t\t<\/div><\/div>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t

\n\t\t\t\t\t\tBezpo\u015bredni link\n\t\t\t\t\t<\/h2><\/div><\/div>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t
\t\t\t\t
\n\t\t\t\t\t

\"\"<\/a><\/p>\n\t\t\t\t<\/div>\n\t\t\t<\/div><\/div>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"

Autorzy Szczeg\u00f3\u0142y publikacji Streszczenie Streszczenie publikacji Bezpo\u015bredni link<\/p>\n","protected":false},"author":4,"featured_media":9193,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[43],"tags":[],"class_list":["post-9720","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-bez-kategorii"],"_links":{"self":[{"href":"https:\/\/evorain.com\/pl\/wp-json\/wp\/v2\/posts\/9720"}],"collection":[{"href":"https:\/\/evorain.com\/pl\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/evorain.com\/pl\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/evorain.com\/pl\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/evorain.com\/pl\/wp-json\/wp\/v2\/comments?post=9720"}],"version-history":[{"count":2,"href":"https:\/\/evorain.com\/pl\/wp-json\/wp\/v2\/posts\/9720\/revisions"}],"predecessor-version":[{"id":10096,"href":"https:\/\/evorain.com\/pl\/wp-json\/wp\/v2\/posts\/9720\/revisions\/10096"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/evorain.com\/pl\/wp-json\/wp\/v2\/media\/9193"}],"wp:attachment":[{"href":"https:\/\/evorain.com\/pl\/wp-json\/wp\/v2\/media?parent=9720"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/evorain.com\/pl\/wp-json\/wp\/v2\/categories?post=9720"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/evorain.com\/pl\/wp-json\/wp\/v2\/tags?post=9720"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}