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.
PASCAL-VOC FSOD Leaderboard
Method |
Venue |
Year |
Backbone |
Detector |
Paradigm |
Setting |
Set1 1/2/3/5/10-shot |
Set2 1/2/3/5/10-shot |
Set3 1/2/3/5/10-shot |
Code |
FS-DETR |
ICCV |
2023 |
R50 |
DETR |
without re-training |
FSOD |
45.0 48.5 51.5 52.7 56.1 |
37.3 41.3 43.4 46.6 49.0 |
43.8 47.1 50.6 52.1 56.9 |
- |
σ-ADP |
ICCV |
2023 |
R-101 |
Faster R-CNN |
meta-learning |
FSOD |
35.9 40.3 49.8 56.8 65.1 |
25.6 30.3 41.7 41.8 50.3 |
33.9 35.6 43.5 47.1 55.9 |
- |
Norm-VAE |
CVPR |
2023 |
R-101 |
Faster-RCNN |
Fine-tuning |
FSOD |
62.1 64.9 67.8 69.2 67.5 |
39.9 46.8 54.4 54.2 53.6 |
58.2 60.3 61.0 64.0 65.5 |
- |
MetaAug |
CVPR |
2023 |
R-101 |
Faster-RCNN |
Fine-tuning |
gFSOD |
66.7 69.3 69.8 72.2 72.1 |
47.7 55.8 61.8 63.9 63.7 |
64.9 65.8 66.2 69.7 70.2 |
- |
MetaAug |
CVPR |
2023 |
R-101 |
Faster-RCNN |
Fine-tuning |
FSOD |
58.4 62.4 63.2 67.6 67.7 |
34.0 43.1 51.0 53.6 54.0 |
55.1 56.6 57.3 62.6 63.7 |
- |
NIFF |
CVPR |
2023 |
R-101 |
Faster-RCNN |
Fine-tuning |
gFSOD |
75.6 76.5 76.7 77.4 76.9 |
70.0 71.4 73.9 74.4 74.0 |
74.4 75.8 76.2 76.6 76.7 |
- |
DiGeo |
CVPR |
2023 |
R-101 |
Faster-RCNN |
Fine-tuning |
gFSOD |
69.7 70.6 72.4 75.4 76.1 |
67.5 68.4 71.4 71.6 73.6 |
68.6 70.9 72.9 74.4 75.0 |
PyTorch |
ICPE |
AAAI |
2023 |
R-101 |
Faster-RCNN |
Fine-tuning |
FSOD |
54.3 59.5 62.4 65.7 66.2 |
33.5 40.1 48.7 51.7 52.5 |
50.9 53.1 55.3 60.6 60.1 |
PyTorch |
VFA |
AAAI |
2023 |
R-101 |
Faster-RCNN |
Fine-tuning |
FSOD |
57.7 64.6 64.7 67.2 67.4 |
41.4 46.2 51.1 51.8 51.6 |
48.9 54.8 56.6 59.0 58.9 |
PyTorch |
D&R |
AAAI |
2023 |
R-101 |
Faster-RCNN |
Fine-tuning |
gFSOD |
41.0 51.7 55.7 61.8 65.4 |
30.7 39.0 42.5 46.6 51.7 |
37.9 47.1 51.7 56.8 59.5 |
PyTorch |
DCFS |
NeurIPS |
2022 |
R-101 |
Faster-RCNN |
Fine-tuning |
FSOD |
56.6 59.6 62.9 65.6 62.5 |
29.7 38.7 46.2 48.9 48.1 |
47.9 51.9 53.3 56.1 59.4 |
PyTorch |
DCFS |
NeurIPS |
2022 |
R-101 |
Faster-RCNN |
Fine-tuning |
gFSOD |
45.8 59.1 62.1 66.8 68.0 |
31.8 41.7 46.6 50.3 53.7 |
39.6 52.1 56.3 60.3 63.3 |
PyTorch |
CoCo-RCNN |
ECCV |
2022 |
R-101 |
Sparse-RCNN |
Fine-tuning |
FSOD |
33.5 44.2 50.2 57.5 63.3 |
25.3 31.0 39.6 43.8 50.1 |
24.8 36.9 42.8 50.8 57.7 |
PyTorch |
FewX |
ECCV |
2022 |
R-50 |
Faster R-CNN |
Fine-tuning |
FSOD |
40.1 44.2 51.2 62.0 63.0 |
33.3 33.1 42.3 46.3 52.3 |
36.1 43.1 43.5 52.0 56.0 |
PyTorch |
MFDC |
ECCV |
2022 |
R-101 |
Faster R-CNN |
Fine-tuning |
FSOD |
63.4 66.3 67.7 69.4 68.1 |
42.1 46.5 53.4 55.3 53.8 |
56.1 58.3 59.0 62.2 63.7 |
PyTorch |
TENET |
ECCV |
2022 |
R-50 |
- |
Fine-tuning |
FSOD |
46.7 - 55.4 62.3 66.9 |
40.3 - 44.7 49.3 52.1 |
35.5 - 46.0 54.4 54.6 |
PyTorch |
MRSN |
ECCV |
2022 |
R-101 |
Faster R-CNN |
Fine-tuning |
FSOD |
47.6 48.6 57.8 61.9 62.6 |
31.2 38.3 46.7 47.1 50.6 |
35.5 30.9 45.6 54.4 57.4 |
- |
KD-DeFRCN |
ECCV |
2022 |
R-101 |
Faster R-CNN |
Fine-tuning |
FSOD |
58.2 62.5 65.1 68.2 67.4 |
37.6 45.6 52.0 54.6 53.2 |
53.8 57.7 58.0 62.4 62.2 |
- |
Label, Verify, Correct |
CVPR |
2022 |
R-101+DINO ViT-S |
Faster R-CNN |
Fine-tuning |
FSOD |
54.5 53.2 58.8 63.2 65.7 |
32.8 29.2 50.7 49.8 50.6 |
48.4 52.7 55.0 59.6 59.6 |
PyTorch |
FCT |
CVPR |
2022 |
PVTv2-B2-Li |
Faster R-CNN |
meta-learning |
FSOD |
38.5 49.6 53.5 59.8 64.3 |
25.9 34.2 40.1 44.9 47.4 |
34.7 43.9 49.3 53.1 56.3 |
PyTorch |
KFSOD |
CVPR |
2022 |
R-50 |
Faster-RCN |
meta-learning |
FSOD |
44.6 - 54.4 60.9 65.8 |
37.8 - 43.1 48.1 50.4 |
34.8 - 44.1 52.7 53.9 |
- |
Meta-Faster-RCNN |
AAAI |
2022 |
R-101 |
Faster R-CNN |
meta-learning |
FSOD |
43.0 54.5 60.6 66.1 65.4 |
27.7 35.5 46.1 47.8 51.4 |
40.6 46.4 53.4 59.9 58.6 |
PyTorch |
QA-FewDet |
ICCV |
2021 |
R-101 |
Faster R-CNN |
meta-learning |
FSOD |
42.4 51.9 55.7 62.6 63.4 |
25.9 37.8 46.6 48.9 51.1 |
35.2 42.9 47.8 54.8 53.5 |
PyTorch |
DeFRCN |
ICCV |
2021 |
R-101 |
Faster R-CNN |
Fine-tuning |
FSOD |
53.6 57.5 61.5 64.1 60.8 |
30.1 38.1 47.0 53.3 47.9 |
48.4 50.9 52.3 54.9 57.4 |
PyTorch |
DeFRCN |
ICCV |
2021 |
R-101 |
Faster R-CNN |
Fine-tuning |
gFSOD |
40.2 53.6 58.2 63.6 66.5 |
29.5 39.7 43.4 48.1 52.8 |
35.0 38.3 52.9 57.7 60.8 |
PyTorch |
FSOD$^{up}$ |
ICCV |
2021 |
R-101 |
Faster R-CNN |
Fine-tuning |
gFSOD |
43.8 47.8 50.3 55.4 61.7 |
31.2 30.5 41.2 42.2 48.3 |
35.5 39.7 43.9 50.6 53.5 |
PyTorch |
FADI |
NeurIPS |
2021 |
R-101 |
Faster R-CNN |
Fine-tuning |
gFSOD |
50.3 54.8 54.2 59.3 63.2 |
30.6 35.0 40.3 42.8 48.0 |
45.7 49.7 49.1 55.0 59.6 |
PyTorch |
SRR-FSD |
CVPR |
2021 |
R-101 |
Faster R-CNN |
Fine-tuning |
FSOD |
47.8 50.5 51.3 55.2 56.8 |
32.5 35.3 39.1 40.8 43.8 |
40.1 41.5 44.3 46.9 46.4 |
- |
CME |
CVPR |
2021 |
|
F-RCNN |
meta-learning |
gFSOD |
41.5 47.5 50.4 58.2 60.9 |
27.2 30.2 41.4 42.5 46.8 |
34.3 39.6 45.1 48.3 51.5 |
PyTorch |
CME |
CVPR |
2021 |
|
Meta-YOLO |
meta-learning |
gFSOD |
17.8 26.1 31.5 44.8 47.5 |
12.7 17.4 27.1 33.7 40.0 |
15.7 27.4 30.7 44.9 48.8 |
PyTorch |
DCNet |
CVPR |
2021 |
R-101 |
Faster R-CNN |
meta-learning |
FSOD |
33.9 37.4 43.7 51.1 59.6 |
23.2 24.8 30.6 36.7 46.6 |
32.3 34.9 39.7 42.6 50.7 |
|
TIP |
CVPR |
2021 |
R-101 |
Faster R-CNN |
meta-learning |
FSOD |
27.7 36.5 43.3 50.2 59.6 |
22.7 30.1 33.8 40.9 46.9 |
21.7 30.6 38.1 44.5 50.9 |
|
FSCE |
CVPR |
2021 |
R-101 |
Faster R-CNN |
Fine-tuning |
FSOD |
32.9 44.0 46.8 52.9 59.7 |
23.7 30.6 38.4 43.0 48.5 |
22.6 33.4 39.5 47.3 54.0 |
PyTorch |
Retentive R-CNN |
CVPR |
2021 |
R-101 |
R-CNN |
Fine-tuning |
gFSOD |
71.3 72.3 72.1 74.0 74.6 |
66.8 68.4 70.2 70.7 71.5 |
69.0 70.9 72.3 73.9 74.1 |
PyTorch |
Halluc |
CVPR |
2021 |
R-101 |
Faster R-CNN |
Fine-tuning |
FSOD |
47.0 44.9 46.5 54.7 54.7 |
26.3 31.8 37.4 37.4 41.2 |
40.4 42.1 43.3 51.4 49.6 |
- |
TFA |
ICML |
2020 |
R-101 |
Faster R-CNN |
Fine-tuning |
FSOD |
39.8 36.1 44.7 55.7 56.0 |
23.5 26.9 34.1 35.1 39.1 |
30.8 34.8 42.8 49.5 49.8 |
PyTorch |
FSDetView |
ECCV |
2020 |
R-101 |
Faster R-CNN |
meta-learning |
FSOD |
24.2 35.3 42.2 49.1 57.4 |
21.6 24.6 31.9 37.0 45.7 |
21.2 30.0 37.2 43.8 49.6 |
PyTorch |
MPSR |
ECCV |
2020 |
R-101 |
Faster R-CNN |
Fine-tuning |
FSOD |
41.7 - 51.4 55.2 61.8 |
24.4 - 39.2 39.9 47.8 |
35.6 - 42.3 48.0 49.7 |
PyTorch |
NP-RepMet |
NeurIPS |
2020 |
R-101 |
Faster R-CNN + DCN |
Fine-tuning |
FSOD |
37.8 40.3 41.7 47.3 49.4 |
41.6 43.0 43.4 47.4 49.1 |
33.3 38.0 39.8 41.5 44.8 |
MXNet |
Contact
e-mail