# All You Need to Know About Training Image Retrieval Models

arXiv: https://arxiv.org/abs/2503.13045 · HTML: https://mlsanity.com/paper/2503.13045/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 24 references that are in the map.
- First posted on arXiv 17 Mar 2025.

## Builds on (most cited first, 14 of 14)

- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020)
- [Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning](https://mlsanity.com/paper/1904.06627/) (2019)
- [A Metric Learning Reality Check](https://mlsanity.com/paper/2003.08505/) (2020)
- [Proxy Anchor Loss for Deep Metric Learning](https://mlsanity.com/paper/2003.13911/) (2020)
- [SoftTriple Loss: Deep Metric Learning Without Triplet Sampling](https://mlsanity.com/paper/1909.05235/) (2019)
- [Revisiting Training Strategies and Generalization Performance in Deep Metric Learning](https://mlsanity.com/paper/2002.08473/) (2020)
- [Signal-to-Noise Ratio: A Robust Distance Metric for Deep Metric Learning](https://mlsanity.com/paper/1904.02616/) (2019)
- [Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning](https://mlsanity.com/paper/2107.09562/) (2021)
- [Unbiased Evaluation of Deep Metric Learning Algorithms](https://mlsanity.com/paper/1911.12528/) (2019)
- [View Independent Vehicle Make, Model and Color Recognition Using Convolutional Neural Network](https://mlsanity.com/paper/1702.01721/) (2017)
- [Threshold-Consistent Margin Loss for Open-World Deep Metric Learning](https://mlsanity.com/paper/2307.04047/) (2023)

## Built on by (most cited first, 1 of 1)

- [Near-perfect photo-ID of the Hula painted frog with zero-shot deep local-feature matching](https://mlsanity.com/paper/2601.08798/) (2026)

## Abstract (arXiv)

Image retrieval is the task of finding images in a database that are most similar to a given query image. The performance of an image retrieval pipeline depends on many training-time factors, including the embedding model architecture, loss function, data sampler, mining function, learning rate(s), and batch size. In this work, we run tens of thousands of training runs to understand the effect each of these factors has on retrieval accuracy. We also discover best practices that hold across multiple datasets. The code is available at https://github.com/gmberton/image-retrieval