A Triplet-loss Dilated Residual Network For High-resolution Representation Learning In Image Retrieval

Abstract

Content-based image retrieval is the process of retrieving a subset of images from an extensive image gallery based on visual contents, such as color, shape or spatial relations, and texture. In some applications, such as localization, image retrieval is employed as the initial step. In such cases, the accuracy of the top-retrieved images significantly affects the overall system accuracy. The current paper introduces a simple yet efficient image retrieval system with a fewer trainable parameters, which offers acceptable accuracy in top-retrieved images. The proposed method benefits from a dilated residual convolutional neural network with triplet loss. Experimental evaluations show that this model can extract richer information (i.e., high-resolution representations) by enlarging the receptive field, thus improving image retrieval accuracy without increasing the depth or complexity of the model. To enhance the extracted representations' robustness, the current research obtains candidat

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyousefzadeh2023a

Related papers

• Enhancing Remote Sensing Image Retrieval With Triplet Deep Metric Learning Network (2019)14.58
• End-to-end Learning Of Deep Visual Representations For Image Retrieval (2016)19.66
• DALG: Deep Attentive Local And Global Modeling For Image Retrieval (2022)0.00
• From Selective Deep Convolutional Features To Compact Binary Representations For Image Retrieval (2018)10.35
• Informative And Representative Triplet Selection For Multilabel Remote Sensing Image Retrieval (2021)10.74
• REMAP: Multi-layer Entropy-guided Pooling Of Dense CNN Features For Image Retrieval (2019)12.33
• Unicom: Universal And Compact Representation Learning For Image Retrieval (2023)5.70
• Bayesian Triplet Loss: Uncertainty Quantification In Image Retrieval (2020)11.49