# Locality Preserving Markovian Transition for Instance Retrieval

arXiv: https://arxiv.org/abs/2506.05196 · HTML: https://mlsanity.com/paper/2506.05196/

## 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 (most cited first, 30 of 37)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [FILIP: Fine-grained Interactive Language-Image Pre-Training](https://mlsanity.com/paper/2111.07783/) (2021)
- [Fine-tuning CNN Image Retrieval with No Human Annotation](https://mlsanity.com/paper/1711.02512/) (2017)
- [Benchmarking Large Language Models in Retrieval-Augmented Generation](https://mlsanity.com/paper/2309.01431/) (2023)
- [Re-ranking Person Re-identification with k-reciprocal Encoding](https://mlsanity.com/paper/1701.08398/) (2017)
- [Large-Scale Image Retrieval with Attentive Deep Local Features](https://mlsanity.com/paper/1612.06321/) (2016)
- [Fast Computation of Wasserstein Barycenters](https://mlsanity.com/paper/1310.4375/) (2013)
- [Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking](https://mlsanity.com/paper/1803.11285/) (2018)
- [Particular object retrieval with integral max-pooling of CNN activations](https://mlsanity.com/paper/1511.05879/) (2015)
- [BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval](https://mlsanity.com/paper/2407.12883/) (2024)
- [End-to-end Learning of Deep Visual Representations for Image Retrieval](https://mlsanity.com/paper/1610.07940/) (2016)
- [A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Ranking](https://mlsanity.com/paper/1711.10378/) (2017)
- [Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations](https://mlsanity.com/paper/1611.05113/) (2016)
- [Correlation Verification for Image Retrieval](https://mlsanity.com/paper/2204.01458/) (2022)
- [Global Features are All You Need for Image Retrieval and Reranking](https://mlsanity.com/paper/2308.06954/) (2023)
- [Multi-Level Optimal Transport for Universal Cross-Tokenizer Knowledge Distillation on Language Models](https://mlsanity.com/paper/2412.14528/) (2024)
- [Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspective](https://mlsanity.com/paper/2012.07620/) (2020)
- [Attention-Based Query Expansion Learning](https://mlsanity.com/paper/2007.08019/) (2020)
- [Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processing](https://mlsanity.com/paper/1811.10907/) (2018)
- [Sinkhorn Distance Minimization for Knowledge Distillation](https://mlsanity.com/paper/2402.17110/) (2024)
- [Contextual Similarity Aggregation with Self-attention for Visual Re-ranking](https://mlsanity.com/paper/2110.13430/) (2021)

## 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.