基于可变形卷积的服装检索方法

计算机工程与科学

基于可变形卷积的服装检索方法

王振，全红艳

（华东师范大学计算机科学与技术学院，上海 200062）

收稿日期:2018-11-27 修回日期:2019-01-08 出版日期:2019-09-25 发布日期:2019-09-25

A garment retrieval method based on deformable convolution

WANG Zhen,QUAN Hong-yan

（School of Computer Science and Technology,East China Normal University,Shanghai 200062,China）

Received:2018-11-27 Revised:2019-01-08 Online:2019-09-25 Published:2019-09-25

摘要/Abstract

摘要：

传统的服装检索方法使用固定形状的感受野，当服装目标存在几何变形时无法有效地提取其特征。针对这个问题，提出基于可变形卷积和相似性学习的服装检索方法。首先，构建可变形卷积网络，自动学习服装特征的采样位置和服装图像的哈希编码；然后，级联相似性学习网络，度量哈希编码的相似性；最后，根据相似性评分产生检索结果。实验结果表明，该方法能够有效地提取存在几何变形的服装目标的特征，从而减少了图像背景特征的干扰，提高了检索模型的准确率。

关键词: 服装检索, 可变形卷积, 哈希编码, 相似性学习

Abstract:

Traditional garment retrieval methods use fixed-shape receptive fields, and they cannot extract features effectively when the garment target has geometric deformation. To solve this problem, we propose a garment retrieval method based on deformable convolution and similarity learning. Firstly, we build a deformable convolutional network which can automatically learn the sampling locations of garment features and the Hash code of garment images. Secondly, a similarity learning network is cascaded to measure the similarity of the Hash code. Finally, we obtain the retrieval results according to similarity scores. Experimental results show that this method can effectively extract the features of garment objects with geometric deformation, thus reducing the impact of image background features and improving the accuracy of the retrieval model.

Key words: garment retrieval, deformable convolution, Hash code, similarity learning

王振，全红艳. 基于可变形卷积的服装检索方法[J]. 计算机工程与科学.

WANG Zhen,QUAN Hong-yan. A garment retrieval method based on deformable convolution[J]. Computer Engineering & Science.

[1]	邓中港, 代刚, 吴湘宁, 邓玉娇, 王稳, 陈苗, 涂雨, 张锋, 方恒. 基于注意力机制和可变形卷积的金属表面细微不规则损伤的图像识别模型[J]. 计算机工程与科学, 2023, 45(01): 127-135.
[2]	强梓林, 刘建国, 刘云峰, 卫栋, 强彦. 基于时域-频域哈希编码的电网图像检索方法[J]. 计算机工程与科学, 2022, 44(10): 1877-1884.
[3]	王雪娇, 智敏. 基于可变形卷积神经网络的人体动作识别[J]. 计算机工程与科学, 2021, 43(01): 105-111.
[4]	邱德红,方少红,孙蕾. 一种基于多阶畸变子模式相似性学习的序列识[J]. J4, 2011, 33(2): 153-158.