Label, Verify, Correct: A Simple Few Shot Object Detection Method
This addresses the problem of expanding object detectors for new categories with limited data for researchers and practitioners in computer vision, representing a strong incremental improvement.
The paper tackles few-shot object detection by introducing a pseudo-labelling method that sources high-quality pseudo-annotations to increase training instances and reduce class imbalance, achieving state-of-the-art or second-best performance on PASCAL VOC and MS-COCO benchmarks across all shot numbers.
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 high-quality 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. Naïvely training with model predictions yields sub-optimal 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 high-quality 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 state-of-the-art or second-best performance compared to existing approaches across all number of shots.