A Triplet-loss Dilated Residual Network for High-Resolution Representation Learning in Image Retrieval

by   Saeideh Yousefzadeh, et al.

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 candidate regions of interest from each feature map and applies Generalized-Mean pooling to the regions. As the choice of triplets in a triplet-based network affects the model training, we employ a triplet online mining method. We test the performance of the proposed method under various configurations on two of the challenging image-retrieval datasets, namely Revisited Paris6k (RPar) and UKBench. The experimental results show an accuracy of 94.54 and 80.23 (mean precision at rank 10) in the RPar medium and hard modes and 3.86 (recall at rank 4) in the UKBench dataset, respectively.


page 4

page 16

page 17


Image Retrieval using Multi-scale CNN Features Pooling

In this paper, we address the problem of image retrieval by learning ima...

Relieving Triplet Ambiguity: Consensus Network for Language-Guided Image Retrieval

Language-guided image retrieval enables users to search for images and i...

End-to-end Learning of Deep Visual Representations for Image Retrieval

While deep learning has become a key ingredient in the top performing me...

On the Unreasonable Effectiveness of Centroids in Image Retrieval

Image retrieval task consists of finding similar images to a query image...

Efficient Region-Based Image Querying

Retrieving images from large and varied repositories using visual conten...

A Pooling Approach to Modelling Spatial Relations for Image Retrieval and Annotation

Over the last two decades we have witnessed strong progress on modeling ...

Improving Deep Binary Embedding Networks by Order-aware Reweighting of Triplets

In this paper, we focus on triplet-based deep binary embedding networks ...

Please sign up or login with your details

Forgot password? Click here to reset