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 2012.14115cs.CV
收藏

有限数据下的类别扩展目标检测器

Towards a category-extended object detector with limited data

Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);TEG AI, Tencent(腾讯TEG人工智能部);Peng Cheng Laboratory(鹏城实验室)

Bowen Zhao, Chen Chen, Xi Xiao, Shutao Xia

摘要:

对象检测器通常在具有固定预定义类别的完全注释的训练数据上学习。然而,类别往往需要逐步增加。通常,在这种情况下,只有用旧类标注的原始训练集和一些用新类标注的新训练数据可用。基于有限的数据集,迫切需要一个能够处理所有类别的统一检测器。我们提出了一个切实可行的方案,以实现它在这项工作。无冲突损失的设计,以避免标签歧义,导致一个可接受的检测器在一个训练轮。为了进一步提高性能,我们提出了一个再训练阶段,在该阶段中,采用Monte Carlo Dropout来计算定位置信度,以挖掘更准确的边界框,并提出了一种加权的方法,以便在再训练过程中更好地利用伪注释。大量的实验证明了我们的方法的有效性。

英文摘要:

Object detectors are typically learned on fully-annotated training data with fixed predefined categories. However, categories are often required to be increased progressively. Usually, only the original training set annotated with old classes and some new training data labeled with new classes are available in such scenarios. Based on the limited datasets, a unified detector that can handle all categories is strongly needed. We propose a practical scheme to achieve it in this work. A conflict-free loss is designed to avoid label ambiguity, leading to an acceptable detector in one training round. To further improve performance, we propose a retraining phase in which Monte Carlo Dropout is employed to calculate the localization confidence to mine more accurate bounding boxes, and an overlap-weighted method is proposed for making better use of pseudo annotations during retraining. Extensive experiments demonstrate the effectiveness of our method.

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。

↑