Achieving visual semantic understanding requires a unified framework that simultaneously handles object detection, category prediction, and attribute recognition. However, current advanced approaches rely on global similarity and struggle to capture fine-grained category distinctions and category-specific attribute diversity, especially in large-scale e-commerce scenarios. To overcome these challenges, we introduce a detection-guided generative framework that predicts hierarchical category and attribute tokens. For each detected object, we extract refined ROI-level features and employ a BART-based generator to produce semantic tokens in a coarse-to-fine sequence covering category hierarchies and property-value pairs, with support for property-conditioned attribute recognition. Experiments on both large-scale proprietary e-commerce datasets and open-source datasets demonstrate that our approach significantly outperforms existing similarity-based pipelines and multi-stage classification systems, achieving stronger fine-grained recognition and more coherent unified inference.
@article{arxiv.2511.15984,
title = {UniDGF: A Unified Detection-to-Generation Framework for Hierarchical Object Visual Recognition},
author = {Xinyu Nan and Lingtao Mao and Huangyu Dai and Zexin Zheng and Xinyu Sun and Zihan Liang and Ben Chen and Yuqing Ding and Chenyi Lei and Wenwu Ou and Han Li},
journal= {arXiv preprint arXiv:2511.15984},
year = {2025}
}