mlsanityData to 7 Oct 2026

LOCORE: Image Re-ranking with Long-Context Sequence Modeling

arXiv 2503.21772 ↗First posted 27 Mar 2025cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

We introduce LOCORE, Long-Context Re-ranker, a model that takes as input local descriptors corresponding to an image query and a list of gallery images and outputs similarity scores between the query and each gallery image. This model is used for image retrieval, where typically a first ranking is performed with an efficient similarity measure, and then a shortlist of top-ranked images is re-ranked based on a more fine-grained similarity measure. Compared to existing methods that perform pair-wise similarity estimation with local descriptors or list-wise re-ranking with global descriptors, LOCORE is the first method to perform list-wise re-ranking with local descriptors. To achieve this, we leverage efficient long-context sequence models to effectively capture the dependencies between query and gallery images at the local-descriptor level. During testing, we process long shortlists with a sliding window strategy that is tailored to overcome the context size limitations of sequence models. Our approach achieves superior performance compared with other re-rankers on established image retrieval benchmarks of landmarks (ROxf and RPar), products (SOP), fashion items (In-Shop), and bird species (CUB-200) while having comparable latency to the pair-wise local descriptor re-rankers.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 42 of its 80 references that are in the map. First posted on arXiv 27 Mar 2025.

Builds on

42 of 80 references.

References · 42

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  5. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  6. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  7. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  8. 2020Longformer: The Long-Document Transformercited by 3,362
  9. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  10. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 935
  11. 2023RWKV: Reinventing RNNs for the Transformer Eracited by 814
  12. 2015Bidirectional LSTM-CRF Models for Sequence Taggingcited by 544
30 more
  1. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 497
  2. 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
  3. 2023Ring Attention with Blockwise Transformers for Near-Infinite Contextcited by 448
  4. 2020Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrievalcited by 305
  5. 2016Large-Scale Image Retrieval with Attentive Deep Local Featurescited by 238
  6. 2024Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attentioncited by 194
  7. 2018Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarkingcited by 189
  8. 2019Span-based Joint Entity and Relation Extraction with Transformer Pre-trainingcited by 132
  9. 2020ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysiscited by 107
  10. 2023R2Former: Unified Retrieval and Reranking Transformer for Place Recognitioncited by 102
  11. 2024Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architecturescited by 97
  12. 2017Semi-supervised sequence tagging with bidirectional language modelscited by 86
  13. 2021Instance-level Image Retrieval using Reranking Transformerscited by 63
  14. 2021DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Featurescited by 54
  15. 2021Recall@k Surrogate Loss with Large Batches and Similarity Mixupcited by 49
  16. 2014Visual Instance Retrieval with Deep Convolutional Networkscited by 48
  17. 2022Correlation Verification for Image Retrievalcited by 47
  18. 2023Global Features are All You Need for Image Retrieval and Rerankingcited by 41
  19. 2019Local Features and Visual Words Emerge in Activationscited by 36
  20. 2022Learning Super-Features for Image Retrievalcited by 35
  21. 2019Combination of Multiple Global Descriptors for Image Retrievalcited by 21
  22. 2020Attention-Based Query Expansion Learningcited by 21
  23. 2023IRGen: Generative Modeling for Image Retrievalcited by 18
  24. 2023Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?cited by 16
  25. 2024AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level Retrievalcited by 16
  26. 2019Sequence Tagging with Contextual and Non-Contextual Subword Representations: A Multilingual Evaluationcited by 14
  27. 2021Contextual Similarity Aggregation with Self-attention for Visual Re-rankingcited by 14
  28. 2021Sequence tagging for biomedical extractive question answeringcited by 12
  29. 2014A Robust Transformation-Based Learning Approach Using Ripple Down Rules for Part-of-Speech Taggingcited by 9
  30. 2022DALG: Deep Attentive Local and Global Modeling for Image Retrievalcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025Patch-wise Retrieval: A Bag of Practical Techniques for Instance-level Matchingcited by 2
  2. 2026ELViS: Efficient Visual Similarity from Local Descriptors that Generalizes Across Domainscited by 1
  3. 2026Indexing Multimodal Language Models for Large-scale Image Retrievalcited by 1
  4. 2026Aerial-ground LiDAR place recognition with patch-level self-supervised learning and expanded reciprocal re-rankingcited by 0
  5. 2026Aggregating Neighbor Embedding Projection and Rank-Based Manifold Learning for Image Retrievalcited by 0