arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.09408cs.CV
收藏

大型视觉模型下的通用目标检测

Universal Object Detection with Large Vision Model

Intellifusion Inc.(云天励飞公司);Harbin Institute of Technology(哈尔滨工业大学);Peng Cheng Laboratory(鹏城实验室);South China University of Technology(华南理工大学)

Feng Lin, Wenze Hu, Yaowei Wang, Yonghong Tian, Guangming Lu, Fanglin Chen, Yong Xu, Xiaoyu Wang

AI总结:

本研究针对大规模多领域通用目标检测问题,提出标签处理、层次感知损失及资源高效训练方法,利用大型视觉模型,在RVC 2022目标检测赛道获第二名,为通用视觉系统提供参考。

摘要:

在过去几年中,人们对开发一个广泛、通用且多用途的计算机视觉系统越来越感兴趣。这样的系统有潜力同时解决广泛的视觉任务,而不受限于特定问题或数据领域。这种通用性对于实际、真实的计算机视觉应用至关重要。在本研究中,我们聚焦于一个具体挑战:大规模、多领域的通用目标检测问题,这有助于实现通用视觉系统的更广泛目标。该问题提出了几个复杂的挑战,包括跨数据集类别标签重复、标签冲突以及处理层次化分类法的必要性。为了应对这些挑战,我们介绍了我们的标签处理方法、层次感知损失设计以及利用预训练大型视觉模型的资源高效模型训练。我们的方法表现出色,在2022年鲁棒视觉挑战赛(RVC 2022)的目标检测赛道中,于百万级跨数据集目标检测基准上获得了令人瞩目的第二名。我们相信,我们的全面研究将为计算机视觉社区解决类似挑战提供有价值的参考和另一种方法。我们的工作源代码公开于https://github.com/linfeng93/Large-UniDet。

英文摘要:

Over the past few years, there has been growing interest in developing a broad, universal, and general-purpose computer vision system. Such systems have the potential to address a wide range of vision tasks simultaneously, without being limited to specific problems or data domains. This universality is crucial for practical, real-world computer vision applications. In this study, our focus is on a specific challenge: the large-scale, multi-domain universal object detection problem, which contributes to the broader goal of achieving a universal vision system. This problem presents several intricate challenges, including cross-dataset category label duplication, label conflicts, and the necessity to handle hierarchical taxonomies. To address these challenges, we introduce our approach to label handling, hierarchy-aware loss design, and resource-efficient model training utilizing a pre-trained large vision model. Our method has demonstrated remarkable performance, securing a prestigious second-place ranking in the object detection track of the Robust Vision Challenge 2022 (RVC 2022) on a million-scale cross-dataset object detection benchmark. We believe that our comprehensive study will serve as a valuable reference and offer an alternative approach for addressing similar challenges within the computer vision community. The source code for our work is openly available at https://github.com/linfeng93/Large-UniDet.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑