论文标题
朝着有限数据的类别扩展对象检测器
Towards a category-extended object detector with limited data
论文作者
论文摘要
对象探测器通常在具有固定预定义类别的完全注重培训数据上学习。但是，通常需要逐步增加类别。通常，在这种情况下，只有旧课程注释的原始培训集和一些带有新课程的新培训数据。基于有限的数据集，强烈需要一个可以处理所有类别的统一检测器。我们提出了一个实用计划，以实现这项工作。无冲突的损失旨在避免标签歧义，从而导致在一次训练回合中可接受的探测器。为了进一步提高性能，我们提出了一个重新培训阶段，其中采用蒙特卡洛辍学术来计算定位置信度以开采更准确的边界框，并提出了一种重叠加权方法，以更好地利用伪注释在重新训练过程中。广泛的实验证明了我们方法的有效性。
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.
