Image hub explorer: evaluating representations and metrics for content-based image retrieval and object recognition

Abstract

We present a novel tool for image data visualization and analysis, Image Hub Explorer. It is aimed at developers and researchers alike and it allows the users to examine various aspects of content-based image retrieval and object recognition under different built-in metrics and models. Image Hub Explorer provides the tools for understanding the distribution of influence in the data, primarily by examining the emerging hub images. Hubness is an aspect of the well-known curse of dimensionality that hampers the effectiveness of many information systems. Its consequences were thoroughly examined in the context of music/audio search and recommendation, but not in case of image retrieval and object recognition. Image Hub Explorer was made with the goal of raising awareness of the hubness phenomenon and offering potential solutions by implementing state-of-the-art hubness-aware metric learning, ranking and classification methods. Various visualization components allow for a quick identification of critical issues and we hope that they will prove helpful in working with large image datasets. We demonstrate the effectiveness of the implemented methods in various object recognition tasks.