The objective of this paper is few-shot object detection
(FSOD) – the task of expanding an object detector for a
new category given only a few instances for training. We
introduce a simple pseudo-labelling method to source highquality pseudo-annotations from the training set, for each
new category, vastly increasing the number of training instances and reducing class imbalance; our method finds
previously unlabelled instances.
Na¨ıvely training with model predictions yields suboptimal performance; we present two novel methods to improve the precision of the pseudo-labelling process: first,
we introduce a verification technique to remove candidate
detections with incorrect class labels; second, we train a
specialised model to correct poor quality bounding boxes.
After these two novel steps, we obtain a large set of highquality pseudo-annotations that allow our final detector to
be trained end-to-end. Additionally, we demonstrate our
method maintains base class performance, and the utility
of simple augmentations in FSOD. While benchmarking on
PASCAL VOC and MS-COCO, our method achieves stateof-the-art or second-best performance compared to existing
approaches across all number of shots.
