Missing labels in object detection

Object detection is a fundamental problem in computer vision. Impressive results have been achieved on large-scale detection benchmarks by fully-supervised object detection (FSOD) methods. However, FSOD performance is highly affected by the quality of annotations available in training. Furthermore, FSOD approaches require tremendous instance-level annotations, which are time-consuming to collect. In contrast, weakly supervised object detection (WSOD) exploits easily-collected image-level labels while it suffers from relatively inferior detection performance. In this paper, we study the effect of missing annotations on FSOD methods and analyze approaches to train an object detector from a hybrid dataset, where both instance-level and image-level labels are employed. Extensive experiments on the challenging PASCAL VOC 2007 and 2012 benchmarks strongly demonstrate the effectiveness of our method, which gives a trade-off between collecting fewer annotations and building a more accurate object detector. Our method is also a strong baseline bridging the wide gap between FSOD and WSOD performances.