# Relative Attribute Classification with Deep Rank SVM

arXiv: https://arxiv.org/abs/2009.07717 · HTML: https://mlsanity.com/paper/2009.07717/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Sep 2020.

## Built on by (most cited first, 4 of 4)

- [Learning semantic image quality for fetal ultrasound from noisy ranking annotation](https://mlsanity.com/paper/2402.08294/) (2024)
- [Variational Self-Supervised Contrastive Learning Using Beta Divergence](https://mlsanity.com/paper/2312.00824/) (2023)
- [Video-Text Temporal Localization via Multi-Scale Convolution and Dynamic Routing](https://mlsanity.com/paper/2607.05093/) (2026)
- [Segmentation Pre-training for Label-Efficient Lumbar Spine Degeneration Grading](https://mlsanity.com/paper/2608.04810/) (2026)

## Abstract (arXiv)

Relative attributes indicate the strength of a particular attribute between image pairs. We introduce a deep Siamese network with rank SVM loss function, called Deep Rank SVM (DRSVM), in order to decide which one of a pair of images has a stronger presence of a specific attribute. The network is trained in an end-to-end fashion to jointly learn the visual features and the ranking function. We demonstrate the effectiveness of our approach against the state-of-the-art methods on four image benchmark datasets: LFW-10, PubFig, UTZap50K-lexi and UTZap50K-2 datasets. DRSVM surpasses state-of-art in terms of the average accuracy across attributes, on three of the four image benchmark datasets.