Bags of Local Convolutional Features for Scalable Instance Search
Bags of Local Convolutional Features for Scalable Instance Search
复制标题
DOI：
10.1145/2911996.2912061
复制
发表时间：
2016-04
期刊：
影响因子：
--
通讯作者：
Eva Mohedano;Amaia Salvador;Kevin McGuinness;F. Marqués;N. O’Connor;Xavier Giro-i-Nieto
中科院分区：
文献类型：
--
作者：
Eva Mohedano;Amaia Salvador;Kevin McGuinness;F. Marqués;N. O’Connor;Xavier Giro-i-Nieto
本文提出了一种简单的实例检索流水线，该流水线利用词袋聚合方案(BOW)对CNN的卷积特征进行编码。将卷积层中的激活的每个局部阵列分配给视觉单词产生分配映射，这是将图像的区域与视觉单词相关联的紧凑表示。我们使用赋值映射进行快速空间重排序，获得用于查询扩展的对象定位。我们演示了基于局部CNN特征的弓表示的适宜性，例如检索，在牛津和巴黎建筑基准上获得了具有竞争力的性能。我们表明，我们提出的基于BOW的CNN特征聚合系统在具有挑战性的TRECVid INS基准测试的子集上优于使用和池的最先进技术。
This work proposes a simple instance retrieval pipeline based on encoding the convolutional features of CNN using the bag of words aggregation scheme (BoW). Assigning each local array of activations in a convolutional layer to a visual word produces an assignment map, a compact representation that relates regions of an image with a visual word. We use the assignment map for fast spatial reranking, obtaining object localizations that are used for query expansion. We demonstrate the suitability of the BoW representation based on local CNN features for instance retrieval, achieving competitive performance on the Oxford and Paris buildings benchmarks. We show that our proposed system for CNN feature aggregation with BoW outperforms state-of-the-art techniques using sum pooling at a subset of the challenging TRECVid INS benchmark.