In object detection, the cost of labeling is much high because it needs not only to confirm the categories of multiple objects in an image but also to accurately determine the bounding boxes of each object. Thus, integrating active learning into object detection will raise pretty positive significance. In this paper, we propose a classification committee for active deep object detection method by introducing a discrepancy mechanism of multiple classifiers for samples' selection when training object detectors. The model contains a main detector and a classification committee. The main detector denotes the target object detector trained from a labeled pool composed of the selected informative images. The role of the classification committee is to select the most informative images according to their uncertainty values from the view of classification, which is expected to focus more on the discrepancy and representative of instances. Specifically, they compute the uncertainty for a specified instance within the image by measuring its discrepancy output by the committee pre-trained via the proposed Maximum Classifiers Discrepancy Group Loss (MCDGL). The most informative images are finally determined by selecting the ones with many high-uncertainty instances. Besides, to mitigate the impact of interference instances, we design a Focus on Positive Instances Loss (FPIL) to make the committee the ability to automatically focus on the representative instances as well as precisely encode their discrepancies for the same instance. Experiments are conducted on Pascal VOC and COCO datasets versus some popular object detectors. And results show that our method outperforms the state-of-the-art active learning methods, which verifies the effectiveness of the proposed method.

翻译：在目标检测中，标注成本极高，因为这不仅需要确认图像中多个物体的类别，还需精确定位每个物体的边界框。因此，将主动学习融入目标检测具有重大的积极意义。本文通过引入多个分类器的差异性机制来筛选训练目标检测器时的样本，提出一种用于主动式深度目标检测的分类委员会方法。该模型包含主检测器和分类委员会两部分。主检测器指由标注池（由所选信息量丰富的图像组成）训练得到的目标检测器。分类委员会的作用是从分类视角出发，根据样本的不确定度值筛选出最具信息量的图像，旨在更关注实例的差异性与代表性。具体而言，委员会通过测量由所提出的最大分类器差异性组损失预训练的模型对图像中特定实例的输出差异，来计算该实例的不确定度。最终通过选取包含大量高不确定度实例的图像来确定最具信息量的图像。此外，为降低干扰实例的影响，我们设计了正实例聚焦损失，使委员会能够自动聚焦代表性实例，并对同一实例的差异进行精确编码。在Pascal VOC和COCO数据集上，与多种主流目标检测器进行对比实验，结果表明该方法优于现有最先进的主动学习方法，验证了所提方法的有效性。