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 | Training-free | AP | 36.6 | — | Unverified |
| 2 | CD-ViTO | AP | 35.3 | — | Unverified |
| 3 | DE-ViT | AP | 34 | — | Unverified |
| 4 | BIOT | AP | 26.3 | — | Unverified |
| 5 | RISF (SWIN-Large) | AP | 25.5 | — | Unverified |
| 6 | DETReg-ft-full DDETR | AP | 25 | — | Unverified |
| 7 | imTED+ViT-B | AP | 22.5 | — | Unverified |
| 8 | hANMCL | AP | 22.4 | — | Unverified |
| 9 | RISF (Resnet-101) | AP | 21.9 | — | Unverified |
| 10 | DCFS | AP | 19.5 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | FS-CDIS (iFS-RCNN+ITL 5-shot) | box AP | 10.36 | — | Unverified |
| 2 | FS-CDIS (MTFA+IMS 5-shot) | box AP | 10.36 | — | Unverified |
| 3 | FS-CDIS (Res101-MTFA+IMS 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 |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Training-free | AP | 36.8 | — | Unverified |
| 2 | CD-ViTO | AP | 35.9 | — | Unverified |
| 3 | DE-ViT | AP | 34 | — | Unverified |
| 4 | BIOT | AP | 33.8 | — | Unverified |
| 5 | RISF (SWIN-Large) | AP | 31.9 | — | Unverified |
| 6 | imTED+ViT-B | AP | 30.2 | — | Unverified |
| 7 | DETReg-ft-full DDETR | AP | 30 | — | Unverified |
| 8 | hANMCL | AP | 25 | — | Unverified |
| 9 | RISF (Resnet-101) | AP | 24.4 | — | Unverified |
| 10 | Meta-DETR (Multi-Scale Feature) | AP | 22.9 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | best_single_model_val | AP | 47.55 | — | Unverified |
| 2 | htc | AP | 39.05 | — | Unverified |
| 3 | Organizer Provided Baseline | AP | 27.26 | — | Unverified |
| 4 | null | AP | 25.8 | — | Unverified |
| 5 | Forest R-CNN | AP | 23.2 | — | Unverified |
| 6 | person | AP | 21.82 | — | Unverified |
| 7 | test balloon 6 | AP | 16.62 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | TestConsistency | AP | 48.58 | — | Unverified |
| 2 | ps4 | AP | 39.67 | — | Unverified |
| 3 | Asynchronous SSL | AP | 37.72 | — | Unverified |
| 4 | CenterNet2 | AP | 35.84 | — | Unverified |
| 5 | Organizer Provided Baseline | AP | 26.86 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Grounding DINO 1.5 Pro | Average Score | 66.3 | — | Unverified |
| 2 | MQ-GLIP-T | Average Score | 57 | — | Unverified |
| 3 | GLIP-T | Average Score | 50.7 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Grounding DINO 1.5 Pro | Average Score | 54.7 | — | Unverified |
| 2 | MQ-GLIP-T | Average Score | 43 | — | Unverified |
| 3 | GLIP-T | Average Score | 38.9 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | DETReg (ours) | AP | 30 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | UniFS | AP | 18.2 | — | Unverified |