Shuffled-Xception-DarkNet-53: A content-based image retrieval model based on deep learning algorithm. (April 2023)

• Record Type: Journal Article
• Authors: Pathak, Debanjan; Raju, U.S.N.
• Is Part Of: Computers & electrical engineering. Volume 107(2023)
• Publication Date: 2023-04
• Subjects: CBIR -- Deep learning -- Xception concept -- Channel shuffle -- DarkNet-53 -- Group convolution; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2023.108647
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: An advanced version of darknet-53, Shuffled-Xception-Darknet-53, is proposed. A total of 5 Shuffled-Xception Module is incorporated with Darknet-53. Three sets of 5 × 5, 3 × 3, and 1 × 1 filters are used in each Shuffled-Xception module. Group Convolution is used in Xception module for informative feature extraction. One Channel Shuffle layer is used between every two Group Convolution layers. Abstract: This paper proposes Shuffled-Xception-DarkNet-53, an advanced version of DarkNet-53 for Content-Based Image Retrieval (CBIR). The proposed model introduced the notion of the Shuffled -Xception module, which uses three sets of 1 × 1, 3 × 3, and 5 × 5 size filters using a serial connection in place of a single 3 × 3 size filter to extract more refined features from the input images. Instead of the standard 2D Convolution operation, 'Group Convolution' is employed in the proposed Shuffled -Xception module to make the training process of the proposed CNN more efficient. Furthermore, 'Group Convolution' improves the co-relations among the filters of the corresponding Shuffled -Xception module, resulting in more informative features. Between every two serial Group Convolution layers of the same size, one Channel Shuffle layer is used to prevent the loss of information flow among the channels of different groups. The proposed method outperformed the twelve compared methods, including conventional and CNN-based CBIR methods, in ten standard image datasets. Graphical abstract: Image, graphical abstract