Few-Shot Object Detection Leaderboard
The goal of this page is to keep on track with the state-of-the-art (SOTA) for the few-shot object detection.
If your paper is not in the list, please feel free to raise an issue or drop me an e-mail.
MSCOCO FSOD Leaderboard
Method |
Venue |
Year |
Backbone |
Detector |
Paradigm |
Setting |
COCO 1/5/10/30-shot AP |
Code |
FS-DETR |
ICCV |
2023 |
R50 |
DETR |
without re-training |
FSOD |
7.0/10.9/11.3/- |
- |
σ-ADP |
ICCV |
2023 |
R-101 |
Faster R-CNN |
meta-learning |
FSOD |
-/-/20.3/22.8 |
- |
Norm-VAE |
CVPR |
2023 |
R-101 |
Faster-RCNN |
Fine-tuning |
FSOD |
9.5/15.9/18.7/22.5 |
- |
MetaAug |
CVPR |
2023 |
R-101 |
Faster-RCNN |
Fine-tuning |
FSOD |
-/-/24.4/28.0 |
- |
MetaAug |
CVPR |
2023 |
R-101 |
Faster-RCNN |
Fine-tuning |
FSOD |
-/-/18.8/23.4 |
- |
NIFF |
CVPR |
2023 |
R-101 |
Faster-RCNN |
Fine-tuning |
gFSOD |
-/33.1/34.0/34.5 |
- |
DiGeo |
CVPR |
2023 |
R-101 |
Faster-RCNN |
Fine-tuning |
gFSOD |
-/-/32.0/33.1 |
PyTorch |
ICPE |
AAAI |
2023 |
R-101 |
Faster-RCNN |
Fine-tuning |
FSOD |
-/-/19.3/23.1 |
PyTorch |
VFA |
AAAI |
2023 |
R-101 |
Faster-RCNN |
Fine-tuning |
FSOD |
-/-/16.2/18.9 |
PyTorch |
D&R |
AAAI |
2023 |
R-101 |
Faster-RCNN |
Fine-tuning |
gFSOD |
6.1/13.9/16.4/20.0 |
PyTorch |
DCFS |
NeurIPS |
2022 |
R-101 |
Faster-RCNN |
Fine-tuning |
FSOD |
8.1/16.6/19.5/22.7 |
PyTorch |
DCFS |
NeurIPS |
2022 |
R-101 |
Faster-RCNN |
Fine-tuning |
gFSOD |
6.2/15.7/18.3/21.9 |
PyTorch |
CoCo-RCNN |
ECCV |
2022 |
R-101 |
Sparse-RCNN |
Fine-tuning |
FSOD |
5.2/-/16.4/19.2 |
PyTorch |
FewX |
ECCV |
2022 |
R-50 |
Faster R-CNN |
Fine-tuning |
FSOD |
-/15.1/-/- |
PyTorch |
MFDC |
ECCV |
2022 |
R-101 |
Faster R-CNN |
Fine-tuning |
FSOD |
10.8/16.4/19.4/22.7 |
PyTorch |
AcroFOD |
ECCV |
2022 |
- |
YOLOv5 |
Fine-tuning |
- |
-/-/-/- |
PyTorch |
TENET |
ECCV |
2022 |
R-50 |
- |
Fine-tuning |
FSOD |
-/-/19.1/- |
PyTorch |
MoFSOD |
ECCV |
2022 |
R-50 |
Faster RCNN |
Fine-tuning |
- |
-/-/-/- |
- |
MRSN |
ECCV |
2022 |
R-101 |
Faster R-CNN |
Fine-tuning |
FSOD |
-/-/15.7/17.5 |
- |
KD-DeFRCN |
ECCV |
2022 |
R-101 |
Faster R-CNN |
Fine-tuning |
FSOD |
-/-/18.9/22.6 |
- |
DETReg |
CVPR |
2022 |
DETReg |
Deformable DETR |
Fine-tuning |
gFSOD |
-/-/~~25.0~~/~~30.0~~ |
PyTorch |
Label, Verify, Correct |
CVPR |
2022 |
R-101+DINO ViT-S |
Faster R-CNN |
Fine-tuning |
FSOD |
-/-/17.8/24.5 |
PyTorch |
Sylph |
CVPR |
2022 |
R-50 |
Faster R-CNN |
meta-learning |
iFSOD |
-/-/-/- |
- |
FCT |
CVPR |
2022 |
PVTv2-B2-Li |
Faster R-CNN |
meta-learning |
FSOD |
5.6/14.0/17.1/21.4 |
PyTorch |
KFSOD |
CVPR |
2022 |
R-50 |
Faster-RCN |
meta-learning |
FSOD |
-/-/18.5/- |
- |
Meta-Faster-RCNN |
AAAI |
2022 |
R-101 |
Faster R-CNN |
meta-learning |
FSOD |
5.1/10.8/12.7/16.6 |
PyTorch |
QA-FewDet |
ICCV |
2021 |
R-101 |
Faster R-CNN |
meta-learning |
FSOD |
4.9/9.7/11.6/16.5 |
PyTorch |
DeFRCN |
ICCV |
2021 |
R-101 |
Faster R-CNN |
Fine-tuning |
FSOD |
7.7/15.9/18.5/22.6 |
PyTorch |
DeFRCN |
ICCV |
2021 |
R-101 |
Faster R-CNN |
Fine-tuning |
gFSOD |
4.8/13.6/16.8/21.2 |
PyTorch |
FSOD$^{up}$ |
ICCV |
2021 |
R-101 |
Faster R-CNN |
Fine-tuning |
gFSOD |
-/-/11.0/15.6 |
PyTorch |
DAnA |
TMM |
2021 |
R-50 |
Faster R-CNN |
meta-learning |
FSOD |
-/-/18.6/21.6 |
PyTorch |
FADI |
NeurIPS |
2021 |
R-101 |
Faster R-CNN |
Fine-tuning |
gFSOD |
5.7/10.1/12.2/16.1 |
PyTorch |
SRR-FSD |
CVPR |
2021 |
R-101 |
Faster R-CNN |
Fine-tuning |
FSOD |
-/-/11.3/14.7 |
- |
MTFA |
CVPR |
2021 |
R-50 |
Faster R-CNN |
Fine-tuning |
gFSOD |
2.4/6.6/8.5/- |
PyTorch |
IMTFA |
CVPR |
2021 |
R-50 |
Faster R-CNN |
Fine-tuning |
iFSOD |
3.3/6.2/7.1/- |
PyTorch |
CME |
CVPR |
2021 |
YOLO |
Meta YOLO |
meta-learning |
gFSOD |
-/-/15.1/16.9 |
PyTorch |
DCNet |
CVPR |
2021 |
R-101 |
Faster R-CNN |
meta-learning |
FSOD |
-/-/12.8/18.6 |
|
TIP |
CVPR |
2021 |
R-101 |
Faster R-CNN |
meta-learning |
FSOD |
-/-/16.3/18.3 |
- |
FSCE |
CVPR |
2021 |
R-101 |
Faster R-CNN |
Fine-tuning |
FSOD |
-/-/11.1/15.3 |
PyTorch |
Retentive R-CNN |
CVPR |
2021 |
R-101 |
R-CNN |
Fine-tuning |
gFSOD |
-/8.3/10.5/13.8 |
PyTorch |
Halluc |
CVPR |
2021 |
R-101 |
Faster R-CNN |
Fine-tuning |
FSOD |
4.4/-/-/- |
- |
FSOD-ARPN-MRD |
CVPR |
2020 |
R-50 |
Faster R-CNN |
meta-learning |
MetaTest |
-/-/-/-/ |
- |
ONCE |
CVPR |
2020 |
ResNet |
CentreNet |
Meta-learning |
iFSOD |
-/-/-/-/ |
- |
TFA |
ICML |
2020 |
R-101 |
Faster R-CNN |
Fine-tuning |
FSOD |
-/-/10.0/13.7 |
PyTorch |
TFA |
ICML |
2020 |
R-101 |
Faster R-CNN |
Fine-tuning |
gFSOD |
1.9/7.0/9.1/12.1 |
PyTorch |
FSDetView |
ECCV |
2020 |
R-101 |
Faster R-CNN |
meta-learning |
FSOD |
-/-/12.5/14.7 |
PyTorch |
MPSR |
ECCV |
2020 |
R-101 |
Faster R-CNN |
Fine-tuning |
FSOD |
-/-/9.8/14.1 |
PyTorch |
NP-RepMet |
NeurIPS |
2020 |
R-101 |
Faster R-CNN + DCN |
Fine-tuning |
FSOD |
-/-/-/- |
MXNet |
Meta-RCNN |
ACM-MM |
2020 |
R-101 |
Faster R-CNN |
Meta-learning |
FSOD |
-/-/8.7/12.4 |
- |
Contact
e-mail