# Deep Relative Attributes

arXiv: https://arxiv.org/abs/1512.04103 · HTML: https://mlsanity.com/paper/1512.04103/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Dec 2015.

## Built on by (most cited first, 12 of 12)

- [Learning to Predict Visual Attributes in the Wild](https://mlsanity.com/paper/2106.09707/) (2021)
- [HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling](https://mlsanity.com/paper/2303.02700/) (2023)
- [RankSRGAN: Super Resolution Generative Adversarial Networks with Learning to Rank](https://mlsanity.com/paper/2107.09427/) (2021)
- [Zero-shot Voice Conversion via Self-supervised Prosody Representation Learning](https://mlsanity.com/paper/2110.14422/) (2021)
- [Learning semantic image quality for fetal ultrasound from noisy ranking annotation](https://mlsanity.com/paper/2402.08294/) (2024)
- [Give me a hint! Navigating Image Databases using Human-in-the-loop Feedback](https://mlsanity.com/paper/1809.08714/) (2018)
- [Deep Bayesian Active Learning-to-Rank with Relative Annotation for Estimation of Ulcerative Colitis Severity](https://mlsanity.com/paper/2409.04952/) (2024)
- [PrefGen: Preference Guided Image Generation with Relative Attributes](https://mlsanity.com/paper/2304.00185/) (2023)
- [Graph Neural Networks to Predict Customer Satisfaction Following Interactions with a Corporate Call Center](https://mlsanity.com/paper/2102.00420/) (2021)
- [Compressive Self-localization Using Relative Attribute Embedding](https://mlsanity.com/paper/2208.08863/) (2022)
- [Automatic Speech Disentanglement for Voice Conversion using Rank Module and Speech Augmentation](https://mlsanity.com/paper/2306.12259/) (2023)
- [Video-Text Temporal Localization via Multi-Scale Convolution and Dynamic Routing](https://mlsanity.com/paper/2607.05093/) (2026)

## Abstract (arXiv)

Visual attributes are great means of describing images or scenes, in a way both humans and computers understand. In order to establish a correspondence between images and to be able to compare the strength of each property between images, relative attributes were introduced. However, since their introduction, hand-crafted and engineered features were used to learn increasingly complex models for the problem of relative attributes. This limits the applicability of those methods for more realistic cases. We introduce a deep neural network architecture for the task of relative attribute prediction. A convolutional neural network (ConvNet) is adopted to learn the features by including an additional layer (ranking layer) that learns to rank the images based on these features. We adopt an appropriate ranking loss to train the whole network in an end-to-end fashion. Our proposed method outperforms the baseline and state-of-the-art methods in relative attribute prediction on various coarse and fine-grained datasets. Our qualitative results along with the visualization of the saliency maps show that the network is able to learn effective features for each specific attribute. Source code of the proposed method is available at https://github.com/yassersouri/ghiaseddin.