# Spreading vectors for similarity search

arXiv: https://arxiv.org/abs/1806.03198 · HTML: https://mlsanity.com/paper/1806.03198/

## Key facts

- Cited by 118 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jun 2018.

## Built on by (most cited first, 30 of 118)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers](https://mlsanity.com/paper/2102.01454/) (2021)
- [The Stable Signature: Rooting Watermarks in Latent Diffusion Models](https://mlsanity.com/paper/2303.15435/) (2023)
- [A Cookbook of Self-Supervised Learning](https://mlsanity.com/paper/2304.12210/) (2023)
- [A Self-Supervised Descriptor for Image Copy Detection](https://mlsanity.com/paper/2202.10261/) (2022)
- [Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology](https://mlsanity.com/paper/2408.00738/) (2024)
- [Exploring scalable medical image encoders beyond text supervision](https://mlsanity.com/paper/2401.10815/) (2024)
- [Sonata: Self-Supervised Learning of Reliable Point Representations](https://mlsanity.com/paper/2503.16429/) (2025)
- [Large-scale Training of Foundation Models for Wearable Biosignals](https://mlsanity.com/paper/2312.05409/) (2023)
- [Training Vision Transformers for Image Retrieval](https://mlsanity.com/paper/2102.05644/) (2021)
- [A General-Purpose Self-Supervised Model for Computational Pathology](https://mlsanity.com/paper/2308.15474/) (2023)
- [MAUVE Scores for Generative Models: Theory and Practice](https://mlsanity.com/paper/2212.14578/) (2022)
- [Mahalanobis++: Improving OOD Detection via Feature Normalization](https://mlsanity.com/paper/2505.18032/) (2025)
- [Neural Networks Learn Statistics of Increasing Complexity](https://mlsanity.com/paper/2402.04362/) (2024)
- [A generalizable 3D framework and model for self-supervised learning in medical imaging](https://mlsanity.com/paper/2501.11755/) (2025)
- [Learning-Augmented k-means Clustering](https://mlsanity.com/paper/2110.14094/) (2021)
- [Regular Polytope Networks](https://mlsanity.com/paper/2103.15632/) (2021)
- [Linking Neural Collapse and L2 Normalization with Improved Out-of-Distribution Detection in Deep Neural Networks](https://mlsanity.com/paper/2209.08378/) (2022)
- [Divergence Frontiers for Generative Models: Sample Complexity, Quantization Effects, and Frontier Integrals](https://mlsanity.com/paper/2106.07898/) (2021)
- [Advancing human-centric AI for robust X-ray analysis through holistic self-supervised learning](https://mlsanity.com/paper/2405.01469/) (2024)
- [Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions](https://mlsanity.com/paper/2507.00191/) (2025)
- [Learning-based Support Estimation in Sublinear Time](https://mlsanity.com/paper/2106.08396/) (2021)
- [Wearable Accelerometer Foundation Models for Health via Knowledge Distillation](https://mlsanity.com/paper/2412.11276/) (2024)
- [In Pursuit of Pixel Supervision for Visual Pre-training](https://mlsanity.com/paper/2512.15715/) (2025)
- [Self-Supervised Video Similarity Learning](https://mlsanity.com/paper/2304.03378/) (2023)
- [EchoApex: A General-Purpose Vision Foundation Model for Echocardiography](https://mlsanity.com/paper/2410.11092/) (2024)
- [Enhancing Network Initialization for Medical AI Models Using Large-Scale, Unlabeled Natural Images](https://mlsanity.com/paper/2308.07688/) (2023)
- [Self-supervised visual learning in the low-data regime: a comparative evaluation](https://mlsanity.com/paper/2404.17202/) (2024)
- [Estimating the electrical power output of industrial devices with end-to-end time-series classification in the presence of label noise](https://mlsanity.com/paper/2105.00349/) (2021)
- [FunnyNet-W: Multimodal Learning of Funny Moments in Videos in the Wild](https://mlsanity.com/paper/2401.04210/) (2024)

## Abstract (arXiv)

Discretizing multi-dimensional data distributions is a fundamental step of modern indexing methods. State-of-the-art techniques learn parameters of quantizers on training data for optimal performance, thus adapting quantizers to the data. In this work, we propose to reverse this paradigm and adapt the data to the quantizer: we train a neural net which last layer forms a fixed parameter-free quantizer, such as pre-defined points of a hyper-sphere. As a proxy objective, we design and train a neural network that favors uniformity in the spherical latent space, while preserving the neighborhood structure after the mapping. We propose a new regularizer derived from the Kozachenko--Leonenko differential entropy estimator to enforce uniformity and combine it with a locality-aware triplet loss. Experiments show that our end-to-end approach outperforms most learned quantization methods, and is competitive with the state of the art on widely adopted benchmarks. Furthermore, we show that training without the quantization step results in almost no difference in accuracy, but yields a generic catalyzer that can be applied with any subsequent quantizer.