mlsanityData to 7 Oct 2026

Billion-scale similarity search with GPUs

arXiv 1702.08734 ↗First posted 28 Feb 2017cs.CV cs.DB cs.DScited by 2,477

Not on the map. Why?

Cited by 333 in Retrieval-augmented generation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Similarity search finds application in specialized database systems handling complex data such as images or videos, which are typically represented by high-dimensional features and require specific indexing structures. This paper tackles the problem of better utilizing GPUs for this task. While GPUs excel at data-parallel tasks, prior approaches are bottlenecked by algorithms that expose less parallelism, such as k-min selection, or make poor use of the memory hierarchy. We propose a design for k-selection that operates at up to 55% of theoretical peak performance, enabling a nearest neighbor implementation that is 8.5x faster than prior GPU state of the art. We apply it in different similarity search scenarios, by proposing optimized design for brute-force, approximate and compressed-domain search based on product quantization. In all these setups, we outperform the state of the art by large margins. Our implementation enables the construction of a high accuracy k-NN graph on 95 million images from the Yfcc100M dataset in 35 minutes, and of a graph connecting 1 billion vectors in less than 12 hours on 4 Maxwell Titan X GPUs. We have open-sourced our approach for the sake of comparison and reproducibility.

Key facts. Cited by 2,477 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Feb 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 252; 2022: 358; 2023: 462; 2024: 431; 2025: 431; 2026: 542.

2,477 papers.

Sort:

By area:

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  3. 2025Qwen3-VL Technical Reportcited by 2,534
  4. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  5. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  6. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  7. 2024Grounding Image Matching in 3D with MASt3Rcited by 960
  8. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 814
  9. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  10. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  11. 2022Galactica: A Large Language Model for Sciencecited by 736
  12. 2023In-Context Retrieval-Augmented Language Modelscited by 694
38 more
  1. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  2. 2021Learning To Retrieve Prompts for In-Context Learningcited by 641
  3. 2023DataComp: In search of the next generation of multimodal datasetscited by 635
  4. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 622
  5. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 609
  6. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  7. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 539
  8. 2021Datasets: A Community Library for Natural Language Processingcited by 526
  9. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 519
  10. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  11. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 464
  12. 2021Large Dual Encoders Are Generalizable Retrieverscited by 454
  13. 2021Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modelingcited by 429
  14. 2024Understanding the planning of LLM agents: A surveycited by 414
  15. 2023Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defensecited by 401
  16. 2023Augmented Language Models: a Surveycited by 398
  17. 2023Med-Flamingo: a Multimodal Medical Few-shot Learnercited by 387
  18. 2021A Survey on Automated Fact-Checkingcited by 376
  19. 2024The Faiss librarycited by 370
  20. 2022Text and Code Embeddings by Contrastive Pre-Trainingcited by 358
  21. 2022Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classificationcited by 355
  22. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  23. 2023NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Railscited by 347
  24. 2021Deep ViT Features as Dense Visual Descriptorscited by 327
  25. 2023CodeT5+: Open Code Large Language Models for Code Understanding and Generationcited by 327
  26. 2022Matryoshka Representation Learningcited by 268
  27. 2021Beyond Goldfish Memory: Long-Term Open-Domain Conversationcited by 266
  28. 2023ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systemscited by 259
  29. 2023The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learningcited by 251
  30. 2023Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Timecited by 247
  31. 2021Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Samplingcited by 238
  32. 2022Promptagator: Few-shot Dense Retrieval From 8 Examplescited by 233
  33. 2024Generative Representational Instruction Tuningcited by 227
  34. 2021Contrastive Learning Inverts the Data Generating Processcited by 220
  35. 2022Memorizing Transformerscited by 219
  36. 2021Internet-Augmented Dialogue Generationcited by 217
  37. 2024CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusioncited by 211
  38. 2023Landmark Attention: Random-Access Infinite Context Length for Transformerscited by 206

50 most cited of 2,477 All 2,477 (JSON)