# End-to-End Localization and Ranking for Relative Attributes

arXiv: https://arxiv.org/abs/1608.02676 · HTML: https://mlsanity.com/paper/1608.02676/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Aug 2016.

## Built on by (most cited first, 9 of 9)

- [Learning Conditional Attributes for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2305.17940/) (2023)
- [Large-Scale Attribute-Object Compositions](https://mlsanity.com/paper/2105.11373/) (2021)
- [Give me a hint! Navigating Image Databases using Human-in-the-loop Feedback](https://mlsanity.com/paper/1809.08714/) (2018)
- [FashionSearchNet-v2: Learning Attribute Representations with Localization for Image Retrieval with Attribute Manipulation](https://mlsanity.com/paper/2111.14145/) (2021)
- [PrefGen: Preference Guided Image Generation with Relative Attributes](https://mlsanity.com/paper/2304.00185/) (2023)
- [Anticipating Object State Changes in Long Procedural Videos](https://mlsanity.com/paper/2405.12789/) (2024)
- [Recognizing Unseen States of Unknown Objects by Leveraging Knowledge Graphs](https://mlsanity.com/paper/2307.12179/) (2023)
- [Graph Neural Networks to Predict Customer Satisfaction Following Interactions with a Corporate Call Center](https://mlsanity.com/paper/2102.00420/) (2021)
- [Scalable Visual Attribute Extraction through Hidden Layers of a Residual ConvNet](https://mlsanity.com/paper/2104.00161/) (2021)

## Abstract (arXiv)

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.