Innovation
Methods, ideas, or system contributions that make the work stand out.
Cross-modal hashing
Fractional diffusion
Scale-decomposable
Multi-length Hamming space
Relevance resolution bottleneck
Relevance-Resolution Transfer via Scale-Decomposable Fractional Diffusion for Multi-Length Cross-Modal Hash Retrieval
🤖 AI Summary
This study addresses the bottleneck in cross-modal hashing retrieval where multi-label semantic relationships struggle to maintain ranking consistency within limited Hamming spaces. To overcome this, we propose the MultiBit framework, which introduces a scale-decomposable fractional relational teacher model. By leveraging fractional diffusion models, this approach transfers multi-label relevance resolution across multi-length Hamming spaces. Specifically, it employs fractional differential equations to model local-to-long-range dependencies and integrates nested prefix coding with Hamming ranking alignment to establish a mapping mechanism between continuous diffusion scales and discrete bit sub-blocks. Experimental results demonstrate that the proposed framework significantly improves retrieval accuracy across multiple benchmark datasets, effectively breaking through existing relevance resolution limitations.
📝 Abstract
Cross-modal hashing enables efficient retrieval by encoding heterogeneous data into compact binary codes. Recent methods exploit fine-grained relations encoded in multi-label training structure, yet none of them constrains how those relations survive as consistent candidate rankings in finite, multi-length Hamming spaces, which we term the relevance resolution bottleneck (RRB). To address the RRB, we propose MultiBit, which transfers relevance resolution from multi-label structure to multi-length Hamming spaces. MultiBit first constructs a scale-decomposable fractional relation teacher from dataset-level label co-occurrence and label specificity, and models dependencies from local to long-range over continuous diffusion scales. It then maps the discretized diffusion scales and their quadrature weights to scale-aware bit subblocks of the maximum-length code, organizes the target code lengths as nested prefixes, and aligns their Hamming candidate rankings with the teacher relations. Experiments on multiple benchmarks demonstrate improved retrieval accuracy. Code is available in the supplementary material.
🔎 Similar Papers
No similar papers found.
