论文标题
弱监督对象检测的主动学习策略
Active Learning Strategies for Weakly-supervised Object Detection
论文作者
论文摘要
接受注释较弱的对象探测器是全面监督的替代方案。但是，它们之间仍然存在显着的性能差距。我们建议通过微调预先训练的弱监督检测器来缩小这一差距，并使用``Box-In-box''（BIB）自动从训练集中选择了一些完全清醒的样品，这是一种专门针对弱势知意的失败模式而设计的新型活跃学习策略，该策略旨在解决弱势知意的失败模式。 VOC07和可可基准的实验表明，围嘴表现优于其他活跃的学习技术，并显着改善了基本的弱监督探测器的性能，而每个类别只有几个全面的图像。围嘴达到了完全监督的快速RCNN的97％，而在VOC07上仅10％的全面宣布图像。在可可（Coco）上，平均每类使用10张全面宣布的图像，或同等的训练集的1％，也减少了弱监督检测器和完全监督的快速RCNN之间的性能差距（IN AP）以上，表现出良好的绩效和数据效率之间的良好权衡。我们的代码可在https://github.com/huyvvo/bib上公开获取。
Object detectors trained with weak annotations are affordable alternatives to fully-supervised counterparts. However, there is still a significant performance gap between them. We propose to narrow this gap by fine-tuning a base pre-trained weakly-supervised detector with a few fully-annotated samples automatically selected from the training set using ``box-in-box'' (BiB), a novel active learning strategy designed specifically to address the well-documented failure modes of weakly-supervised detectors. Experiments on the VOC07 and COCO benchmarks show that BiB outperforms other active learning techniques and significantly improves the base weakly-supervised detector's performance with only a few fully-annotated images per class. BiB reaches 97% of the performance of fully-supervised Fast RCNN with only 10% of fully-annotated images on VOC07. On COCO, using on average 10 fully-annotated images per class, or equivalently 1% of the training set, BiB also reduces the performance gap (in AP) between the weakly-supervised detector and the fully-supervised Fast RCNN by over 70%, showing a good trade-off between performance and data efficiency. Our code is publicly available at https://github.com/huyvvo/BiB.
