Claudio Michaelis, Ivan Ustyuzhaninov, Matthias Bethge, Alexander S. Ecker
We tackle the problem of one-shot instance segmentation: Given an example image of a novel, previously unknown object category, find and segment all objects of this category within a complex scene. To address this challenging new task, we propose Siamese Mask R-CNN. It extends Mask R-CNN by a Siamese backbone encoding both reference image and scene, allowing it to target detection and segmentation towards the reference category. 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. Our work provides a first strong baseline for one-shot instance segmentation and will hopefully inspire further research into more powerful and flexible scene analysis algorithms. Code is available at: https://github.com/bethgelab/siamese-mask-rcnn
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Object Detection | COCO (Common Objects in Context) | AP 0.5 | 16.3 | Siamese Mask R-CNN |
| 3D | COCO (Common Objects in Context) | AP 0.5 | 16.3 | Siamese Mask R-CNN |
| Instance Segmentation | COCO (Common Objects in Context) | AP 0.5 | 14.5 | Siamese Mask R-CNN |
| 2D Classification | COCO (Common Objects in Context) | AP 0.5 | 16.3 | Siamese Mask R-CNN |
| 2D Object Detection | COCO (Common Objects in Context) | AP 0.5 | 16.3 | Siamese Mask R-CNN |
| 16k | COCO (Common Objects in Context) | AP 0.5 | 16.3 | Siamese Mask R-CNN |