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

arXiv: https://arxiv.org/abs/2303.08398 · HTML: https://mlsanity.com/paper/2303.08398/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 57 references that are in the map.
- First posted on arXiv 15 Mar 2023.

## Builds on (most cited first, 30 of 35)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [Fine-tuning CNN Image Retrieval with No Human Annotation](https://mlsanity.com/paper/1711.02512/) (2017)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [Dilated Residual Networks](https://mlsanity.com/paper/1705.09914/) (2017)
- [Sampling Matters in Deep Embedding Learning](https://mlsanity.com/paper/1706.07567/) (2017)
- [Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking](https://mlsanity.com/paper/1803.11285/) (2018)
- [Learning Fine-grained Image Similarity with Deep Ranking](https://mlsanity.com/paper/1404.4661/) (2014)
- [Particular object retrieval with integral max-pooling of CNN activations](https://mlsanity.com/paper/1511.05879/) (2015)
- [Deep Image Retrieval: Learning global representations for image search](https://mlsanity.com/paper/1604.01325/) (2016)
- [Learning Deep Structure-Preserving Image-Text Embeddings](https://mlsanity.com/paper/1511.06078/) (2015)
- [End-to-end Learning of Deep Visual Representations for Image Retrieval](https://mlsanity.com/paper/1610.07940/) (2016)
- [An Analysis of Deep Neural Network Models for Practical Applications](https://mlsanity.com/paper/1605.07678/) (2016)
- [Deep Metric Learning with Hierarchical Triplet Loss](https://mlsanity.com/paper/1810.06951/) (2018)
- [Benchmark Analysis of Representative Deep Neural Network Architectures](https://mlsanity.com/paper/1810.00736/) (2018)
- [On the Performance of ConvNet Features for Place Recognition](https://mlsanity.com/paper/1501.04158/) (2015)
- [Deep Learning for Instance Retrieval: A Survey](https://mlsanity.com/paper/2101.11282/) (2021)
- [Improved Embeddings with Easy Positive Triplet Mining](https://mlsanity.com/paper/1904.04370/) (2019)
- [Aggregating Deep Convolutional Features for Image Retrieval](https://mlsanity.com/paper/1510.07493/) (2015)
- [CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples](https://mlsanity.com/paper/1604.02426/) (2016)
- [Visual Instance Retrieval with Deep Convolutional Networks](https://mlsanity.com/paper/1412.6574/) (2014)
- [Cross-dimensional Weighting for Aggregated Deep Convolutional Features](https://mlsanity.com/paper/1512.04065/) (2015)
- [Leveraging Deep Visual Descriptors for Hierarchical Efficient Localization](https://mlsanity.com/paper/1809.01019/) (2018)

## Abstract (arXiv)

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.