mlsanityData to 7 Oct 2026

DeDrift: Robust Similarity Search under Content Drift

arXiv 2308.02752 ↗First posted 5 Aug 2023cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

The statistical distribution of content uploaded and searched on media sharing sites changes over time due to seasonal, sociological and technical factors. We investigate the impact of this "content drift" for large-scale similarity search tools, based on nearest neighbor search in embedding space. Unless a costly index reconstruction is performed frequently, content drift degrades the search accuracy and efficiency. The degradation is especially severe since, in general, both the query and database distributions change. We introduce and analyze real-world image and video datasets for which temporal information is available over a long time period. Based on the learnings, we devise DeDrift, a method that updates embedding quantizers to continuously adapt large-scale indexing structures on-the-fly. DeDrift almost eliminates the accuracy degradation due to the query and database content drift while being up to 100x faster than a full index reconstruction.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 21 of its 50 references that are in the map. First posted on arXiv 5 Aug 2023.

Builds on

21 of 50 references.

References · 21

  1. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  2. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  3. 2017Billion-scale similarity search with GPUscited by 2,477
  4. 2020Linformer: Self-Attention with Linear Complexitycited by 1,462
  5. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  6. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  7. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 853
  8. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 497
  9. 2022A Self-Supervised Descriptor for Image Copy Detectioncited by 175
  10. 2021Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samplescited by 114
  11. 2017Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graphcited by 103
  12. 2022Results of the NeurIPS'21 Challenge on Billion-Scale Approximate Nearest Neighbor Searchcited by 45
9 more
  1. 2021The 2021 Image Similarity Dataset and Challengecited by 44
  2. 2018Revisiting the Inverted Indices for Billion-Scale Approximate Nearest Neighborscited by 37
  3. 2021FreshDiskANN: A Fast and Accurate Graph-Based ANN Index for Streaming Similarity Searchcited by 36
  4. 2020Similarity Search for Efficient Active Learning and Search of Rare Conceptscited by 24
  5. 2019Defense Against Adversarial Images using Web-Scale Nearest-Neighbor Searchcited by 19
  6. 2022TPU-KNN: K Nearest Neighbor Search at Peak FLOP/scited by 18
  7. 2022OOD-DiskANN: Efficient and Scalable Graph ANNS for Out-of-Distribution Queriescited by 14
  8. 2017Online Product Quantizationcited by 11
  9. 2020K-means for Evolving Data Streamscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 5; 2026: 1.

11 papers.

  1. 2024The Faiss librarycited by 370
  2. 2024TabReD: Analyzing Pitfalls and Filling the Gaps in Tabular Deep Learning Benchmarkscited by 29
  3. 2025Inference-time sparse attention with asymmetric indexingcited by 11
  4. 2024Locally-Adaptive Quantization for Streaming Vector Searchcited by 10
  5. 2025Quake: Adaptive Indexing for Vector Searchcited by 8
  6. 2024Incremental IVF Index Maintenance for Streaming Vector Searchcited by 7
  7. 2025Cracking Vector Search Indexescited by 3
  8. 2025Lossless Compression of Vector IDs for Approximate Nearest Neighbor Searchcited by 1
  9. 2024Vector search with small radiusescited by 0
  10. 2025Individualized non-uniform quantization for vector searchcited by 0
  11. 2026A Power Law in Logarithm's Clothing: On the Scalability of Graph-Based Vector Searchcited by 0