# ELViS: Efficient Visual Similarity from Local Descriptors that Generalizes Across Domains

arXiv: https://arxiv.org/abs/2603.28603 · HTML: https://mlsanity.com/paper/2603.28603/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 52 of its 72 references that are in the map.
- First posted on arXiv 30 Mar 2026.

## Builds on (most cited first, 30 of 52)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [Fine-tuning CNN Image Retrieval with No Human Annotation](https://mlsanity.com/paper/1711.02512/) (2017)
- [Generalizing to Unseen Domains via Adversarial Data Augmentation](https://mlsanity.com/paper/1805.12018/) (2018)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval](https://mlsanity.com/paper/2004.01804/) (2020)
- [Learning to Learn Single Domain Generalization](https://mlsanity.com/paper/2003.13216/) (2020)
- [A Fourier-based Framework for Domain Generalization](https://mlsanity.com/paper/2105.11120/) (2021)
- [Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data](https://mlsanity.com/paper/1909.00889/) (2019)
- [Large-Scale Image Retrieval with Attentive Deep Local Features](https://mlsanity.com/paper/1612.06321/) (2016)
- [Image Matching across Wide Baselines: From Paper to Practice](https://mlsanity.com/paper/2003.01587/) (2020)
- [Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking](https://mlsanity.com/paper/1803.11285/) (2018)
- [AnyLoc: Towards Universal Visual Place Recognition](https://mlsanity.com/paper/2308.00688/) (2023)
- [MAGSAC++, a fast, reliable and accurate robust estimator](https://mlsanity.com/paper/1912.05909/) (2019)
- [Robust and Generalizable Visual Representation Learning via Random Convolutions](https://mlsanity.com/paper/2007.13003/) (2020)
- [FoundPose: Unseen Object Pose Estimation with Foundation Features](https://mlsanity.com/paper/2311.18809/) (2023)
- [R2Former: Unified Retrieval and Reranking Transformer for Place Recognition](https://mlsanity.com/paper/2304.03410/) (2023)
- [Deep Lattice Networks and Partial Monotonic Functions](https://mlsanity.com/paper/1709.06680/) (2017)

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

- [Indexing Multimodal Language Models for Large-scale Image Retrieval](https://mlsanity.com/paper/2604.13268/) (2026)

## Abstract (arXiv)

Large-scale instance-level training data is scarce, so models are typically trained on domain-specific datasets. Yet in real-world retrieval, they must handle diverse domains, making generalization to unseen data critical. We introduce ELViS, an image-to-image similarity model that generalizes effectively to unseen domains. Unlike conventional approaches, our model operates in similarity space rather than representation space, promoting cross-domain transfer. It leverages local descriptor correspondences, refines their similarities through an optimal transport step with data-dependent gains that suppress uninformative descriptors, and aggregates strong correspondences via a voting process into an image-level similarity. This design injects strong inductive biases, yielding a simple, efficient, and interpretable model. To assess generalization, we compile a benchmark of eight datasets spanning landmarks, artworks, products, and multi-domain collections, and evaluate ELViS as a re-ranking method. Our experiments show that ELViS outperforms competing methods by a large margin in out-of-domain scenarios and on average, while requiring only a fraction of their computational cost. Code available at: https://github.com/pavelsuma/ELViS/