mlsanityData to 14 Oct 2026

Locality Preserving Markovian Transition for Instance Retrieval

arXiv 2506.05196 ↗First posted 5 Jun 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Diffusion-based re-ranking methods are effective in modeling the data manifolds through similarity propagation in affinity graphs. However, positive signals tend to diminish over several steps away from the source, reducing discriminative power beyond local regions. To address this issue, we introduce the Locality Preserving Markovian Transition (LPMT) framework, which employs a long-term thermodynamic transition process with multiple states for accurate manifold distance measurement. The proposed LPMT first integrates diffusion processes across separate graphs using Bidirectional Collaborative Diffusion (BCD) to establish strong similarity relationships. Afterwards, Locality State Embedding (LSE) encodes each instance into a distribution for enhanced local consistency. These distributions are interconnected via the Thermodynamic Markovian Transition (TMT) process, enabling efficient global retrieval while maintaining local effectiveness. Experimental results across diverse tasks confirm the effectiveness of LPMT for instance retrieval.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 37 of its 73 references that are in the map. First posted on arXiv 5 Jun 2025.

Builds on

37 of 73 references.

References · 37

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023Visual Instruction Tuningcited by 7,869
  3. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  4. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  5. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  6. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  7. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,619
  8. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  9. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  10. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
  11. 2021FILIP: Fine-grained Interactive Language-Image Pre-Trainingcited by 627
  12. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 499
25 more
  1. 2023Benchmarking Large Language Models in Retrieval-Augmented Generationcited by 312
  2. 2017Re-ranking Person Re-identification with k-reciprocal Encodingcited by 262
  3. 2016Large-Scale Image Retrieval with Attentive Deep Local Featurescited by 238
  4. 2013Fast Computation of Wasserstein Barycenterscited by 216
  5. 2018Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarkingcited by 191
  6. 2015Particular object retrieval with integral max-pooling of CNN activationscited by 161
  7. 2024BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrievalcited by 158
  8. 2016End-to-end Learning of Deep Visual Representations for Image Retrievalcited by 122
  9. 2017A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Rankingcited by 74
  10. 2016Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representationscited by 50
  11. 2022Correlation Verification for Image Retrievalcited by 47
  12. 2023Global Features are All You Need for Image Retrieval and Rerankingcited by 41
  13. 2024Multi-Level Optimal Transport for Universal Cross-Tokenizer Knowledge Distillation on Language Modelscited by 36
  14. 2020Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspectivecited by 24
  15. 2020Attention-Based Query Expansion Learningcited by 21
  16. 2018Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processingcited by 20
  17. 2024Sinkhorn Distance Minimization for Knowledge Distillationcited by 15
  18. 2021Contextual Similarity Aggregation with Self-attention for Visual Re-rankingcited by 14
  19. 2022Self-Taught Metric Learning without Labelscited by 13
  20. 2017Fast Spectral Ranking for Similarity Searchcited by 12
  21. 2023Graph Convolution Based Efficient Re-Ranking for Visual Retrievalcited by 11
  22. 2023Contextually Affinitive Neighborhood Refinery for Deep Clusteringcited by 10
  23. 2020PyRetri: A PyTorch-based Library for Unsupervised Image Retrieval by Deep Convolutional Neural Networkscited by 5
  24. 2022Supervised Metric Learning to Rank for Retrieval via Contextual Similarity Optimizationcited by 5
  25. 2024Cluster-Aware Similarity Diffusion for Instance Retrievalcited by 1

Built on by

Not cited yet.