# UniDGF: A Unified Detection-to-Generation Framework for Hierarchical Object Visual Recognition

Source: [UniDGF: A Unified Detection-to-Generation Framework for Hierarchical Object Visual Recognition](<https://www.sota2.com/research/paper/691ff231d6b0dd334292e7f0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-11-22T05:02:37.875Z

Authors: Xinyu Nan, Lingtao Mao, Huangyu Dai, Zexin Zheng, Xinyu Sun, Zihan Liang, Ben Chen, Yuqing Ding, Chenyi Lei, Wenwu Ou, Han Li

Published: 2025-11-20T02:37:43.000Z

## Abstract

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.

## 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](<https://arxiv.org/abs/2511.15984>)

[PDF](<https://arxiv.org/pdf/2511.15984.pdf>)
