arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.16013cs.CV
收藏

半监督开放世界目标检测

Semi-supervised Open-World Object Detection

Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);Linköping University(林雪平大学)

Sahal Shaji Mullappilly, Abhishek Singh Gehlot, Rao Muhammad Anwer, Fahad Shahbaz Khan, Hisham Cholakkal

AI总结:

针对传统开放世界目标检测增量学习阶段依赖大量人工标注的问题,提出半监督开放世界检测设定及SS-OWFormer检测器,通过特征对齐和伪标签方案利用少量标注与大量无标注数据,在4个数据集上验证了有效性。

摘要:

传统开放世界目标检测(OWOD)问题设定首先区分已知类别和未知类别,随后在后续任务中引入标签时再增量学习未知目标。然而,当前的OWOD公式化设定在增量学习阶段严重依赖外部人工专家提供知识输入,这种对运行时人工干预的依赖使得该设定在实际部署中不够贴合现实场景。为解决这一问题,我们提出了一种更具现实性的设定,名为半监督开放世界检测(SS-OWOD),该设定通过将OWOD的增量学习阶段以半监督方式开展,从而降低标注成本。我们证明,在提出的SS-OWOD设定下,当前最先进的OWOD检测器的性能会急剧下降。因此,我们提出了一种新型SS-OWOD检测器,名为SS-OWFormer,它利用特征对齐方案,更好地对齐原始图像与增强图像之间的目标查询表征,以利用大量无标注数据和少量有标注数据。我们进一步提出了一种用于未知目标检测的伪标签方案,该方案利用解码器目标查询捕捉目标特定信息的固有能力。我们针对遥感目标检测验证了所提SS-OWOD问题设定与方法的有效性,同时提出了精心整理的数据集划分方案与基线性能评估结果。我们在包括MS COCO、PASCAL、Objects365和DOTA在内的4个数据集上开展的实验证明了我们方法的有效性。我们的源代码、模型和数据集划分方案可在此处获取:https://github.com/sahalshajim/SS-OWFormer

英文摘要:

Conventional open-world object detection (OWOD) problem setting first distinguishes known and unknown classes and then later incrementally learns the unknown objects when introduced with labels in the subsequent tasks. However, the current OWOD formulation heavily relies on the external human oracle for knowledge input during the incremental learning stages. Such reliance on run-time makes this formulation less realistic in a real-world deployment. To address this, we introduce a more realistic formulation, named semi-supervised open-world detection (SS-OWOD), that reduces the annotation cost by casting the incremental learning stages of OWOD in a semi-supervised manner. We demonstrate that the performance of the state-of-the-art OWOD detector dramatically deteriorates in the proposed SS-OWOD setting. Therefore, we introduce a novel SS-OWOD detector, named SS-OWFormer, that utilizes a feature-alignment scheme to better align the object query representations between the original and augmented images to leverage the large unlabeled and few labeled data. We further introduce a pseudo-labeling scheme for unknown detection that exploits the inherent capability of decoder object queries to capture object-specific information. We demonstrate the effectiveness of our SS-OWOD problem setting and approach for remote sensing object detection, proposing carefully curated splits and baseline performance evaluations. Our experiments on 4 datasets including MS COCO, PASCAL, Objects365 and DOTA demonstrate the effectiveness of our approach. Our source code, models and splits are available here - https://github.com/sahalshajim/SS-OWFormer

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。

↑