OntoAug：以本体引导重新审视生成式数据增强
OntoAug: Rethinking Generative Data Augmentation via Ontology Guidance
把前景掩码与多样化背景提示注入扩散采样过程，实现主体一致、上下文多样的可控合成数据；这套「结构化布局控制 + 提示解耦」思路可直接迁移到任何需要扩充训练集的识别任务，并可作为 WSOL 与 LVLM 推理的增强手段。
原文依据 By explicitly introducing foreground masks and diverse background prompts during the generation process
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论生成式数据增强为提升图像识别模型带来了新的机遇。尽管取得了这些进展，现有大多数增强方法都对图像做整体处理，没有考虑分类任务中判别性信息分布不均的问题——前景主体通常比背景上下文包含更丰富的类别相关信号。忽视这种不均衡会在生成样本中引入非预期的语义漂移，从而削弱模型捕捉目标对象内在本体的能力。事实上，人类的感知也以类似方式运作：主体身份保持稳定，而只要整体连贯性得以保持，上下文的变化会被自然容忍。受此观察启发，我们提出 OntoAug，一个面向本体的数据增强框架，显式区分主体与环境。OntoAug 通过结构化布局控制分离前景与背景，并引导扩散模型生成主体一致、上下文多样的样本。通过在生成过程中显式引入前景掩码与多样化背景提示，该框架同时提升了合成数据的语义保真度与多样性。大量实验表明，OntoAug 在图像分类、少样本学习、弱监督目标定位（WSOL）以及大型视觉语言模型推理等多项任务上均取得强劲性能。
英文原文摘要 1524 字符
Generative data augmentation has created new opportunities for improving image recognition models. Despite these advances, most existing augmentation methods process images holistically, without accounting for the uneven distribution of discriminative information in classification tasks, where foreground subjects typically contain richer category-relevant signals than background context. Ignoring this imbalance can introduce unintended semantic shifts in generated samples, thereby weakening the model's ability to capture the intrinsic ontology of the target object. In fact, human perception operates in a similar manner: subject identity remains stable, while contextual variations are naturally tolerated as long as overall coherence is preserved. Inspired by this observation, we propose OntoAug, an ontology-oriented data augmentation framework that explicitly distinguishes between subject and environment. OntoAug separates foreground and background through structured layout control and guides diffusion models to generate samples with consistent subjects and diverse contextual variations. By explicitly introducing foreground masks and diverse background prompts during the generation process, the framework enhances both semantic fidelity and diversity in the synthesized data. Extensive experiments show that OntoAug achieves strong performance across multiple tasks, including image classification, few-shot learning, weakly supervised object localization (WSOL), and large vision-language model reasoning.