面向跨模态检索的类内分布引导生成哈希与邻居精炼
Intra-class Distribution-guided Generative Hashing with Neighbor Refinement for Cross-modal Retrieval
用类内分布估计加邻居引导修正来生成语义多样的合成样本，可作为一种即插即用的数据增广/难样本构造手段，用于跨模态检索中的哈希码判别性学习。
原文依据 we propose a novel Intra-class Distribution-guided Generative Hashing (IDGH) that adaptively generates synthetic samples directly from estimated intra-class distributions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期跨模态哈希方法引入样本生成策略以丰富训练信号。尽管取得这些进展，样本生成驱动的哈希仍面临两大挑战：（1）基于插值的方法采用确定且与类别无关的生成方式，使合成样本被限制在原始数据附近的小区域内。因此类内多样性受限，削弱了模型学习判别性二进制码的能力。（2）基于生成网络的方法利用复杂的生成模型产生合成样本，导致额外的模型复杂度。为解决这些问题，我们提出一种新颖的类内分布引导生成哈希（IDGH），直接从估计的类内分布自适应地生成合成样本。具体而言，我们提出类内分布估计（IDE）方案来建模每个类的特征分布，为自适应样本生成提供必要支撑。同时，利用相邻类的分布信息，我们设计邻居引导分布精炼（NDR）机制来修正类别中有缺陷的估计。借助精炼后的类内分布，我们提出分布感知自适应生成（DAG）策略，在类内分布模式引导下沿多样方向移动特征，从而合成信息量丰富的训练样本。所提方法即插即用，可无缝集成到各种目标函数中，提供语义多样的训练样本，从而增强相似性学习。在基准数据集上的大量实验表明，IDGH 优于现有方法。代码见 https://github.com/QinLab-WFU/IDGH。
英文原文摘要 1793 字符
Recent cross-modal hashing methods have introduced sample generation strategies to enrich training signals. Despite these advances, sample generation-driven hashing still faces two major challenges: (1) Interpolation-based methods adopt deterministic and class-independent generation that restricts synthetic samples to a small region around the original data. Consequently, intra-class diversity is limited, which weakens the model's ability to learn discriminative binary codes. (2) Generation network-based methods, which leverage a complex generative model to produce synthetic samples, leading to extra model complexity. To address these issues, we propose a novel Intra-class Distribution-guided Generative Hashing (IDGH) that adaptively generates synthetic samples directly from estimated intra-class distributions. Specifically, we suggest an Intra-class Distribution Estimation (IDE) scheme to model the characteristic distribution of each class, providing essential support for adaptive sample generation. Meanwhile, by utilizing the distribution information from neighboring classes, we design a Neighbor-guided Distribution Refinement (NDR) mechanism to correct flawed estimations for classes. With refined intra-class distributions, we propose a Distribution-aware Adaptive Generation (DAG) strategy that synthesizes informative training samples by shifting features along diverse directions guided by intra-class distribution patterns. The proposed approach is plug-and-play and can be seamlessly integrated into various objective functions, providing semantically diverse training samples, thus enhancing similarity learning. Extensive experiments on benchmark datasets demonstrate that IDGH outperforms existing methods. Code is available at https://github.com/QinLab-WFU/IDGH.