Towards Good Practices for Image Retrieval Based on CNN Features

Omar Seddati, Stephane Dupont, Said Mahmoudi, Mahnaz Parian; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 1246-1255

Convolutional Neural Networks (CNNs) have shown their ability to provide effective descriptors for image retrieval. In this paper, we focus on CNN feature extraction for instance-level image search. We started by studying in depth several methods proposed to improve the Regional Maximal Activation (RMAC) approach. Then, we selected some of these advances and introduced a new approach that combines multi-scale and multi-layer feature extraction with feature selection. We also propose an approach for local RMAC descriptor extraction based on class activation maps. Our parameter-free approach provides short descriptors and achieves state-of-the-art performance without the need of CNN finetuning or additional data in any way . In order to demonstrate the effectiveness of our approach, we conducted extensive experiments on four well known instance-level image retrieval benchmarks (the INRIA Holidays dataset, the University of Kentucky Benchmark, Oxford5k and Paris6k).