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.

本文提出了一种使用三元组损失（triplet loss）的卷积神经网络方法，该方法采用膨胀残差卷积神经网络（dilated residual convolutional neural network）提取高分辨率表示，并通过广义均值池化（Generalized-Mean pooling）方法增强提取的表示的鲁棒性，该方法在 Revisited Paris6k 和 UKBench 等数据集上取得良好的图像检索精度。

高分辨率图像检索中基于 Triplet-loss 扩张残差网络的表示学习

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

High-resolution representations (HR) are essential for dense prediction tasks
such as segmentation, detection, and pose estimation. Learning HR
representations is typically ignored in previous Neural Architecture Search
(NAS) methods that focus on image classification. This work proposes a novel
NAS method, called HR-NAS, which is able to find efficient and accurate
networks for different tasks, by effectively encoding multiscale contextual
information while maintaining high-resolution representations. In HR-NAS, we
renovate the NAS search space as well as its searching strategy. To better
encode multiscale image contexts in the search space of HR-NAS, we first
carefully design a lightweight transformer, whose computational complexity can
be dynamically changed with respect to different objective functions and
computation budgets. To maintain high-resolution representations of the learned
networks, HR-NAS adopts a multi-branch architecture that provides convolutional
encoding of multiple feature resolutions, inspired by HRNet. Last, we proposed
an efficient fine-grained search strategy to train HR-NAS, which effectively
explores the search space, and finds optimal architectures given various tasks
and computation resources. HR-NAS is capable of achieving state-of-the-art
trade-offs between performance and FLOPs for three dense prediction tasks and
an image classification task, given only small computational budgets. For
example, HR-NAS surpasses SqueezeNAS that is specially designed for semantic
segmentation while improving efficiency by 45.9%. Code is available at
this https URL

本项研究提出了一种名为 HR-NAS 的新型神经结构搜索方法，采用多分辨率特征编码和轻量级 transformer 来动态产生网络架构，并通过高分辨率肢体姿态分割、目标检测和图像分类等密集预测任务的实验结果证明其能够在小的计算预算下实现最先进的性能和 FLOPs 折衷。