End-to-End Localization and Ranking for Relative Attributes
This work addresses the challenge of attribute-based image analysis for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of simultaneously localizing and ranking relative visual attributes using only weakly-supervised pairwise image comparisons, achieving state-of-the-art ranking results on various datasets and significantly speeding up processing compared to previous methods.
We propose an end-to-end deep convolutional network to simultaneously localize and rank relative visual attributes, given only weakly-supervised pairwise image comparisons. Unlike previous methods, our network jointly learns the attribute's features, localization, and ranker. The localization module of our network discovers the most informative image region for the attribute, which is then used by the ranking module to learn a ranking model of the attribute. Our end-to-end framework also significantly speeds up processing and is much faster than previous methods. We show state-of-the-art ranking results on various relative attribute datasets, and our qualitative localization results clearly demonstrate our network's ability to learn meaningful image patches.