ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2017, Vol. 54 ›› Issue (8): 1824-1832.doi: 10.7544/issn1000-1239.2017.20170197

所属专题: 2017人工智能前沿进展专题

• 人工智能 • 上一篇    下一篇

基于多尺度深度学习的商品图像检索

周晔,张军平   

  1. (复旦大学计算机科学技术学院 上海 200433) (上海市智能信息处理重点实验室 上海 200433) (yezhou14@fudan.edu.cn)
  • 出版日期: 2017-08-01
  • 基金资助: 
    国家自然科学基金项目(61673118);上海市浦江人才计划项目(16PJD009)

Multi-Scale Deep Learning for Product Image Search

Zhou Ye, Zhang Junping   

  1. (School of Computer Science, Fudan University, Shanghai 200433) (Shanghai Key Laboratory of Intelligent Information Processing, Shanghai 200433)
  • Online: 2017-08-01

摘要: 商品图像检索的目标是检索与图像内容相符的商品,它是移动视觉搜索在电子商务中的重要应用.商品图像检索的发展,既为用户购物提供便利,又促进了电子商务向移动端发展.图像特征是影响商品图片检索性能的重要因素.复杂的图片背景、同类商品之间的相似性和被拍摄商品尺度的变化,都使得商品图像检索对图像特征提出了更高的要求.提出了一种多尺度深度神经网络,以便于抽取对复杂图片背景和目标物体尺度变化更加鲁棒的图像特征.同时根据商品类别标注信息学习图片之间的相似度.针对在线服务对响应速度的要求,通过压缩模型的深度和宽度控制了计算开销.在一个百万级的商品图片数据集上的对比实验证明:该方法在保持速度的同时提升了查询的准确率.

关键词: 商品图像检索, 深度学习, 多尺度, 度量学习, 模型压缩

Abstract: Product image search is an important application of mobile visual search in e-commerce. The target of product image search is to retrieve the exact product in a query image. The development of product image search not only facilitates people’s shopping, but also results in that e-commerce moves forward to mobile users. As one of the most important performance factors in product image search, image representation suffers from complicated image background, small variance within each product category, and variant scale of the target object. To deal with complicated background and variant object scale, we present a multi-scale deep model for extracting image representation. Meanwhile, we learn image similarity from product category annotations. We also optimize the computation cost by reducing the width and depth of our model to meet the speed requirements of online search services. Experimental results on a million-scale product image dataset shows that our method improves retrieval accuracy while keeps good computation efficiency, comparing with existing methods.

Key words: product image search, deep learning, multi scale, metric learning, model compression

中图分类号: