Large-scale instance-level image retrieval

Amato G., Carrara F., Falchi F., Gennaro C., Vadicamo L.

Management Science and Operations Research  Computer Science Applications  Image retrieval  Library and Information Sciences  Media Technology  Information Systems  Surrogate text representation  Deep features  Inverted index 

The great success of visual features learned from deep neural networks has led to a significant effort to develop efficient and scalable technologies for image retrieval. Nevertheless, its usage in large-scale Web applications of content-based retrieval is still challenged by their high dimensionality. To overcome this issue, some image retrieval systems employ the product quantization method to learn a large-scale visual dictionary from a training set of global neural network features. These approaches are implemented in main memory, preventing their usage in big-data applications. The contribution of the work is mainly devoted to investigating some approaches to transform neural network features into text forms suitable for being indexed by a standard full-text retrieval engine such as Elasticsearch. The basic idea of our approaches relies on a transformation of neural network features with the twofold aim of promoting the sparsity without the need of unsupervised pre-training. We validate our approach on a recent convolutional neural network feature, namely Regional Maximum Activations of Convolutions (R-MAC), which is a state-of-art descriptor for image retrieval. Its effectiveness has been proved through several instance-level retrieval benchmarks. An extensive experimental evaluation conducted on the standard benchmarks shows the effectiveness and efficiency of the proposed approach and how it compares to state-of-the-art main-memory indexes.

Source: Information processing & management 57 (2019). doi:10.1016/j.ipm.2019.102100

Publisher: Pergamon,, New York , Regno Unito

Metrics