Bags of Local Convolutional Features for Scalable Instance Search
This work addresses scalable instance search for applications like image retrieval, but it is incremental as it builds on existing CNN and BoW methods.
The authors tackled instance retrieval by proposing a bag-of-words aggregation scheme for convolutional neural network features, achieving competitive performance on Oxford and Paris benchmarks and outperforming state-of-the-art methods on a subset of the TRECVid INS benchmark.
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 \textit{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.