# Large-to-small Image Resolution Asymmetry in Deep Metric Learning

arXiv: https://arxiv.org/abs/2210.05463 · HTML: https://mlsanity.com/paper/2210.05463/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 54 references that are in the map.
- First posted on arXiv 11 Oct 2022.

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Fine-tuning CNN Image Retrieval with No Human Annotation](https://mlsanity.com/paper/1711.02512/) (2017)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning](https://mlsanity.com/paper/1904.06627/) (2019)
- [Sampling Matters in Deep Embedding Learning](https://mlsanity.com/paper/1706.07567/) (2017)
- [Fixing the train-test resolution discrepancy](https://mlsanity.com/paper/1906.06423/) (2019)
- [Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates](https://mlsanity.com/paper/1708.07120/) (2017)
- [Learning Fine-grained Image Similarity with Deep Ranking](https://mlsanity.com/paper/1404.4661/) (2014)
- [ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis](https://mlsanity.com/paper/2004.01113/) (2020)
- [Revisiting Training Strategies and Generalization Performance in Deep Metric Learning](https://mlsanity.com/paper/2002.08473/) (2020)
- [Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval](https://mlsanity.com/paper/2007.12163/) (2020)
- [MultiGrain: a unified image embedding for classes and instances](https://mlsanity.com/paper/1902.05509/) (2019)
- [Towards Backward-Compatible Representation Learning](https://mlsanity.com/paper/2003.11942/) (2020)
- [Learning with Privileged Information for Efficient Image Super-Resolution](https://mlsanity.com/paper/2007.07524/) (2020)
- [MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution](https://mlsanity.com/paper/1909.12978/) (2019)
- [Unified Representation Learning for Cross Model Compatibility](https://mlsanity.com/paper/2008.04821/) (2020)
- [Asymmetric metric learning for knowledge transfer](https://mlsanity.com/paper/2006.16331/) (2020)
- [Compatibility-aware Heterogeneous Visual Search](https://mlsanity.com/paper/2105.06047/) (2021)
- [Towards Universal Backward-Compatible Representation Learning](https://mlsanity.com/paper/2203.01583/) (2022)
- [The Group Loss for Deep Metric Learning](https://mlsanity.com/paper/1912.00385/) (2019)
- [Resolution Switchable Networks for Runtime Efficient Image Recognition](https://mlsanity.com/paper/2007.09558/) (2020)

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

- [ILIAS: Instance-Level Image retrieval At Scale](https://mlsanity.com/paper/2502.11748/) (2025)
- [AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level Retrieval](https://mlsanity.com/paper/2408.03282/) (2024)
- [Infusing fine-grained visual knowledge to Vision-Language Models](https://mlsanity.com/paper/2508.12137/) (2025)
- [Learning Compatible Multi-Prize Subnetworks for Asymmetric Retrieval](https://mlsanity.com/paper/2504.11879/) (2025)

## Abstract (arXiv)

Deep metric learning for vision is trained by optimizing a representation network to map (non-)matching image pairs to (non-)similar representations. During testing, which typically corresponds to image retrieval, both database and query examples are processed by the same network to obtain the representation used for similarity estimation and ranking. In this work, we explore an asymmetric setup by light-weight processing of the query at a small image resolution to enable fast representation extraction. The goal is to obtain a network for database examples that is trained to operate on large resolution images and benefits from fine-grained image details, and a second network for query examples that operates on small resolution images but preserves a representation space aligned with that of the database network. We achieve this with a distillation approach that transfers knowledge from a fixed teacher network to a student via a loss that operates per image and solely relies on coupled augmentations without the use of any labels. In contrast to prior work that explores such asymmetry from the point of view of different network architectures, this work uses the same architecture but modifies the image resolution. We conclude that resolution asymmetry is a better way to optimize the performance/efficiency trade-off than architecture asymmetry. Evaluation is performed on three standard deep metric learning benchmarks, namely CUB200, Cars196, and SOP. Code: https://github.com/pavelsuma/raml