Mohedano E, Salvador A, McGuinness K, Giró-i-Nieto X, O'Connor N, Marqués F. Bags of Local Convolutional Features for Scalable Instance Search. In ACM International Conference on Multimedia Retrieval (ICMR). New York City, NY; USA: ACM; 2016.  (3.73 MB)


Image representations extracted from convolutional neural networks (CNNs) have been shown to outperform hand-crafted features in multiple computer vision tasks, such as visual image retrieval. This work proposes a simple pipeline for encoding the local activations of a convolutional layer of a pre-trained CNN using the well-known 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 Bag of Words representation based on local CNN features for image retrieval, achieving state-of-the-art 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.

Best poster award at ACM ICMR 2016

Preprint on arXiv

Project page with source code

Post on GitXiv

Overall acceptance rate in ICMR 2016: 30% 

2016-05-Seminar-AmaiaSalvador-DeepVision from Image Processing Group on Vimeo.