Few-Shot Object Detection
Few-Shot Object Detection is a computer vision task that involves detecting objects in images with limited training data. The goal is to train a model on a few examples of each object class and then use the model to detect objects in new images.
Papers
Showing 1–10 of 179 papers
All datasetsMS-COCO (10-shot)CAMO-FSMS-COCO (30-shot)LVIS v1.0 valMS-COCO (1-shot)LVIS v1.0 test-devODinW-13ODinW-35COCO 2017MS-COCO (5-shot)
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | FS-CDIS (MTFA+IMS 5-shot) | box AP | 10.36 | — | Unverified |
| 2 | FS-CDIS (Res101-MTFA+IMS 5-shot) | box AP | 10.36 | — | Unverified |
| 3 | FS-CDIS (iFS-RCNN+ITL 5-shot) | box AP | 10.36 | — | Unverified |
| 4 | FS-CDIS (Res101-MTFA+ITL 5-shot) | box AP | 9.76 | — | Unverified |
| 5 | FS-CDIS (M-RCNN+ITL 5-shot) | box AP | 9.67 | — | Unverified |
| 6 | FS-CDIS (M-RCNN+IMS 5-shot) | box AP | 9.52 | — | Unverified |
| 7 | FS-CDIS (iFS-RCNN+IMS 5-shot) | box AP | 8.44 | — | Unverified |
| 8 | FS-CDIS (M-RCNN+IMS 3-shot) | box AP | 7.96 | — | Unverified |
| 9 | FS-CDIS (M-RCNN+ITL 3-shot) | box AP | 7.85 | — | Unverified |
| 10 | FS-CDIS (M-RCNN+ITL 2-shot) | box AP | 7.56 | — | Unverified |