Locality Preserving Markovian Transition For Instance Retrieval

Abstract

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 confi

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyluo2025locality

Related papers

• Cluster-aware Similarity Diffusion For Instance Retrieval (2024)0.00
• Hybrid Diffusion: Spectral-temporal Graph Filtering For Manifold Ranking (2018)2.26
• Cross-modal Manifold Learning For Cross-modal Retrieval (2016)0.00
• Deepdiffusion: Unsupervised Learning Of Retrieval-adapted Representations Via Diffusion-based Ranking On Latent Feature Manifold (2021)5.13
• Look Before You Leap: Improving Text-based Person Retrieval By Learning A Consistent Cross-modal Common Manifold (2022)15.34
• Efficient Image Retrieval Via Decoupling Diffusion Into Online And Offline Processing (2018)12.25
• Locality Aware Appearance Metric For Multi-target Multi-camera Tracking (2019)0.00
• Enhancing The Ranking Context Of Dense Retrieval Methods Through Reciprocal Nearest Neighbors (2023)4.52