# Attributed Synthetic Data Generation for Zero-shot Domain-specific Image Classification Source: [Attributed Synthetic Data Generation for Zero-shot Domain-specific Image Classification]() Collection index: [llms.txt]() Data updated: 2025-10-28T13:57:15.407Z Authors: Shijian Wang, Linxin Song, Ryotaro Shimizu, Masayuki Goto, Hanqian Wu Published: 2025-04-06T14:54:10.000Z ## Abstract Zero-shot domain-specific image classification is challenging in classifying real images without ground-truth in-domain training examples. Recent research involved knowledge from texts with a text-to-image model to generate in-domain training images in zero-shot scenarios. However, existing methods heavily rely on simple prompt strategies, limiting the diversity of synthetic training images, thus leading to inferior performance compared to real images. In this paper, we propose AttrSyn, which leverages large language models to generate attributed prompts. These prompts allow for the generation of more diverse attributed synthetic images. Experiments for zero-shot domain-specific image classification on two fine-grained datasets show that training with synthetic images generated by AttrSyn significantly outperforms CLIP's zero-shot classification under most situations and consistently surpasses simple prompt strategies. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()