End-to-End Localization and Ranking for Relative Attributes

Abstract

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.

arXiv commentAppears in European Conference on Computer Vision (ECCV), 2016

References in corpus (3)

• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• DRAW: A Recurrent Neural Network For Image Generation
• Learning Generative Models with Visual Attention

Cited by in corpus (8)

• Automatic Spatially-aware Fashion Concept Discovery
• Weakly-supervised Visual Grounding of Phrases with Linguistic Structures
• Interspecies Knowledge Transfer for Facial Keypoint Detection
• Large-Scale Attribute-Object Compositions
• Modeling Image Virality with Pairwise Spatial Transformer Networks
• Relative Attribute Classification with Deep Rank SVM
• Give me a hint! Navigating Image Databases using Human-in-the-loop Feedback
• Compare and Contrast: Learning Prominent Visual Differences