# Learning Non-Metric Visual Similarity for Image Retrieval

arXiv: https://arxiv.org/abs/1709.01353 · HTML: https://mlsanity.com/paper/1709.01353/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Sep 2017.

## Built on by (most cited first, 5 of 5)

- [Deep Learning for Instance Retrieval: A Survey](https://mlsanity.com/paper/2101.11282/) (2021)
- [ARMBench: An Object-centric Benchmark Dataset for Robotic Manipulation](https://mlsanity.com/paper/2303.16382/) (2023)
- [Scene Graph Embeddings Using Relative Similarity Supervision](https://mlsanity.com/paper/2104.02381/) (2021)
- [CorrEmbed: Evaluating Pre-trained Model Image Similarity Efficacy with a Novel Metric](https://mlsanity.com/paper/2308.16126/) (2023)
- [Indicative Image Retrieval: Turning Blackbox Learning into Grey](https://mlsanity.com/paper/2201.11898/) (2022)

## Abstract (arXiv)

Measuring visual similarity between two or more instances within a data distribution is a fundamental task in image retrieval. Theoretically, non-metric distances are able to generate a more complex and accurate similarity model than metric distances, provided that the non-linear data distribution is precisely captured by the system. In this work, we explore neural networks models for learning a non-metric similarity function for instance search. We argue that non-metric similarity functions based on neural networks can build a better model of human visual perception than standard metric distances. As our proposed similarity function is differentiable, we explore a real end-to-end trainable approach for image retrieval, i.e. we learn the weights from the input image pixels to the final similarity score. Experimental evaluation shows that non-metric similarity networks are able to learn visual similarities between images and improve performance on top of state-of-the-art image representations, boosting results in standard image retrieval datasets with respect standard metric distances.