One-Shot Object Detection
10 papers with code • 2 benchmarks • 3 datasets
( Image credit: Siamese Mask R-CNN )
We demonstrate empirical results on MS Coco highlighting challenges of the one-shot setting: while transferring knowledge about instance segmentation to novel object categories works very well, targeting the detection network towards the reference category appears to be more difficult.
Through the analysis we propose a CNN architecture that is capable of detecting vehicles from aerial UAV images and can operate between 5-18 frames-per-second for a variety of platforms with an overall accuracy of ~95%.
Compared to methods with similar detectors, it boosts almost 10 points of MOTA and significantly decreases the number of ID switches on BDD100K and Waymo datasets.
Distance metric learning (DML) has been successfully applied to object classification, both in the standard regime of rich training data and in the few-shot scenario, where each category is represented by only a few examples.
In this paper, we consider the task of one-shot object detection, which consists in detecting objects defined by a single demonstration.