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 2409.05650cs.CVcs.AI
收藏

用于持续目标检测的带标签传播的重放巩固

Replay Consolidation with Label Propagation for Continual Object Detection

University of Padova(帕多瓦大学);Fondazione Bruno Kessler(布鲁诺·凯塞勒基金会)

Riccardo De Monte, Davide Dalle Pezze, Marina Ceccon, Francesco Pasti, Francesco Paissan, Elisabetta Farella, Gian Antonio Susto, Nicola Bellotto

AI总结:

针对持续目标检测中的缺失标注和任务干扰问题,提出RCLPOD方法,通过类别平衡和标签传播技术提升重放样本及其标注质量,在VOC和COC基准上超越现有技术,并兼容YOLOv8等现代架构。

摘要:

持续学习(CL)旨在学习新数据的同时记住先前获取的知识。与图像分类的CL不同,目标检测的CL面临额外的挑战,例如缺失标注问题。在这种情况下,先前任务的图像可能包含未知类别的实例,这些实例在未来任务中可能作为带标签的实例重新出现,导致基于重放方法的任务干扰。因此,文献中的大多数方法集中于基于蒸馏的技术,当任务之间存在显著的类别重叠时,这些技术是有效的。在我们的工作中,我们提出了一种替代基于蒸馏方法的新方法,称为用于目标检测的带标签传播的重放巩固(RCLPOD)。RCLPOD通过一种促进类别平衡的技术提高存储样本的质量来增强重放记忆,同时通过一种称为标签传播的技术改善与这些样本相关的真实标注的质量。RCLPOD在VOC和COC等成熟基准上优于现有技术。此外,我们的方法被开发用于与YOLOv8等现代架构协同工作,使其适用于自动驾驶和机器人等动态现实应用,在这些应用中,持续学习和资源效率是必不可少的。

英文摘要:

Continual Learning (CL) aims to learn new data while remembering previously acquired knowledge. In contrast to CL for image classification, CL for Object Detection faces additional challenges such as the missing annotations problem. In this scenario, images from previous tasks may contain instances of unknown classes that could reappear as labeled in future tasks, leading to task interference in replay-based approaches. Consequently, most approaches in the literature have focused on distillation-based techniques, which are effective when there is a significant class overlap between tasks. In our work, we propose an alternative to distillation-based approaches with a novel approach called Replay Consolidation with Label Propagation for Object Detection (RCLPOD). RCLPOD enhances the replay memory by improving the quality of the stored samples through a technique that promotes class balance while also improving the quality of the ground truth associated with these samples through a technique called label propagation. RCLPOD outperforms existing techniques on well-established benchmarks such as VOC and COC. Moreover, our approach is developed to work with modern architectures like YOLOv8, making it suitable for dynamic, real-world applications such as autonomous driving and robotics, where continuous learning and resource efficiency are essential.

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。

↑