提出新评估方法，精准检测时尚图文生成中属性错配问题。
Evaluating Attribute Confusion in Fashion Text-to-Image Generation
- 用定位式VQA策略逐个检查实体与属性匹配
- 在新数据集上相比现有方法相关性提升12.3%
- 适合关注生成细节准确性的研究人员
尽管文本到图像（T2I）生成模型快速进展，其评估在时尚领域仍具挑战性，涉及复杂组合生成。现有自动化评估方法依赖预训练视觉语言模型衡量跨模态对齐，但我们的初步研究发现，它们在评估丰富实体-属性语义方面仍有限，难以识别属性混淆问题——即属性虽正确描绘却关联错误实体。为此，我们采用针对单个实体的视觉问答（VQA）定位策略，跨越视觉与文本模态。提出一种局部化人工评估协议，并引入新型自动指标Local VQAScore（L-VQAScore），结合视觉定位与VQA探测正确（反射）和错位（泄漏）属性生成。在新构建的包含挑战性组合对齐场景的数据集上，L-VQAScore相较于现有先进T2I评估方法在与人类判断的相关性上表现更优，证明其在捕捉细粒度实体-属性关联方面的优势。我们认为L-VQAScore可作为主观评估的可靠且可扩展替代方案。
原文摘要 · Abstract (English)
Despite the rapid advances in Text-to-Image (T2I) generation models, their evaluation remains challenging in domains like fashion, involving complex compositional generation. Recent automated T2I evaluation methods leverage pre-trained vision-language models to measure cross-modal alignment. However, our preliminary study reveals that they are still limited in assessing rich entity-attribute semantics, facing challenges in attribute confusion, i.e., when attributes are correctly depicted but associated to the wrong entities. To address this, we build on a Visual Question Answering (VQA) localization strategy targeting one single entity at a time across both visual and textual modalities. We propose a localized human evaluation protocol and introduce a novel automatic metric, Localized VQAScore (L-VQAScore), that combines visual localization with VQA probing both correct (reflection) and miss-localized (leakage) attribute generation. On a newly curated dataset featuring challenging compositional alignment scenarios, L-VQAScore outperforms state-of-the-art T2I evaluation methods in terms of correlation with human judgments, demonstrating its strength in capturing fine-grained entity-attribute associations. We believe L-VQAScore can be a reliable and scalable alternative to subjective evaluations.
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。