提出LPMT框架，提升图像检索中远距离样本的相似性判断能力。
Locality Preserving Markovian Transition for Instance Retrieval
- 通过双向协同扩散整合多图相似性关系
- 利用热力学马尔可夫过程保持局部一致性并实现全局检索
- 适合需要精准长距离相似性建模的图像检索场景
基于扩散的重排序方法通过亲缘图中的相似性传播有效建模数据流形。然而，远离源点的正向信号会随传播步数衰减，削弱了局部以外区域的区分能力。为解决此问题，我们提出局部性保持的马尔可夫转移（LPMT）框架，采用具有多个状态的长期热力学转移过程，实现精确的流形距离测量。LPMT首先通过双向协同扩散（BCD）在多个独立图间融合扩散过程，建立强相似性关系；随后，局部状态嵌入（LSE）将每个实例编码为分布以增强局部一致性；这些分布通过热力学马尔可夫转移（TMT）过程相互连接，既支持高效全局检索，又保持局部有效性。跨多种任务的实验结果验证了LPMT在实例检索中的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。