You are currently viewing a beta version of our website. If you spot anything unusual, kindly let us know.
Altmetrics
Downloads
144
Views
76
Comments
0
A peer-reviewed article of this preprint also exists.
This version is not peer-reviewed
Method | AP | AP |
---|---|---|
MoCo-v3 [32] | 47.9 | 42.7 |
BeiT [2] | 49.8 | 44.4 |
CAE [36] | 50.0 | 44.0 |
SimMIM [35] | 52.3 | - |
MAE [23] | 50.3 | 44.9 |
Ours | 51.3 | 45.6 |
Mask Ratio | Accuracy | Loss Weight | Accuracy | Decoder Depth | Accuracy |
---|---|---|---|---|---|
50% | 79.22 | 0.1 | 78.10 | 1 | 74.89 |
75% | 79.09 | 0.5 | 78.09 | 2 | 78.56 |
80% | 79.25 | 1 | 78.09 | 4 | 80.03 |
90% | 79.23 | 1.5 | 79.31 | 8 | 80.03 |
95% | 78.30 | 2.0 | 79.64 | 12 | 79.11 |
Model | Approach | Training Epochs | Accuracy |
---|---|---|---|
SimCLR [13] | CL | 1000 | 80.4 |
MoCo-v3 [32] | CL | 300 | 83.2 |
DINO [14] | CL | 300 | 82.8 |
CIM [36] | MIM | 300 | 83.3 |
BEiT [2] | MIM | 800 | 83.2 |
SimMIM [35] | MIM | 800 | 83.8 |
CAE [24] | MIM | 1600 | 83.9 |
MAE [23] | MIM | 1600 | 83.6 |
Ours | MIM+CL | 800 | 83.2 |
Ours | MIM+CL | 1600 | 84.3 |
Method | Approach | Pre-training Epochs | Accuracy |
---|---|---|---|
SimCLR [13] | CL | 1000 | 76.5 |
MoCo-v3 [32] | CL | 300 | 76.7 |
DINO [14] | CL | 300 | 78.2 |
BEiT [2] | MIM | 800 | 56.7 |
SimMIM [35] | MIM | 800 | 56.7 |
CAE [24] | MIM | 1600 | 71.4 |
MAE [23] | MIM | 1600 | 68.0 |
Ours | MIM+CL | 1600 | 76.7 |
Methods | Accuracy |
---|---|
Ours | 79.09 |
Ours w/o two different targets | 77.86 |
Ours w/o contrastive loss | 74.33 |
baseline [23] | 76.48 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
Submitted:
04 October 2023
Posted:
09 October 2023
You are already at the latest version
A peer-reviewed article of this preprint also exists.
This version is not peer-reviewed
Submitted:
04 October 2023
Posted:
09 October 2023
You are already at the latest version
Method | AP | AP |
---|---|---|
MoCo-v3 [32] | 47.9 | 42.7 |
BeiT [2] | 49.8 | 44.4 |
CAE [36] | 50.0 | 44.0 |
SimMIM [35] | 52.3 | - |
MAE [23] | 50.3 | 44.9 |
Ours | 51.3 | 45.6 |
Mask Ratio | Accuracy | Loss Weight | Accuracy | Decoder Depth | Accuracy |
---|---|---|---|---|---|
50% | 79.22 | 0.1 | 78.10 | 1 | 74.89 |
75% | 79.09 | 0.5 | 78.09 | 2 | 78.56 |
80% | 79.25 | 1 | 78.09 | 4 | 80.03 |
90% | 79.23 | 1.5 | 79.31 | 8 | 80.03 |
95% | 78.30 | 2.0 | 79.64 | 12 | 79.11 |
Model | Approach | Training Epochs | Accuracy |
---|---|---|---|
SimCLR [13] | CL | 1000 | 80.4 |
MoCo-v3 [32] | CL | 300 | 83.2 |
DINO [14] | CL | 300 | 82.8 |
CIM [36] | MIM | 300 | 83.3 |
BEiT [2] | MIM | 800 | 83.2 |
SimMIM [35] | MIM | 800 | 83.8 |
CAE [24] | MIM | 1600 | 83.9 |
MAE [23] | MIM | 1600 | 83.6 |
Ours | MIM+CL | 800 | 83.2 |
Ours | MIM+CL | 1600 | 84.3 |
Method | Approach | Pre-training Epochs | Accuracy |
---|---|---|---|
SimCLR [13] | CL | 1000 | 76.5 |
MoCo-v3 [32] | CL | 300 | 76.7 |
DINO [14] | CL | 300 | 78.2 |
BEiT [2] | MIM | 800 | 56.7 |
SimMIM [35] | MIM | 800 | 56.7 |
CAE [24] | MIM | 1600 | 71.4 |
MAE [23] | MIM | 1600 | 68.0 |
Ours | MIM+CL | 1600 | 76.7 |
Methods | Accuracy |
---|---|
Ours | 79.09 |
Ours w/o two different targets | 77.86 |
Ours w/o contrastive loss | 74.33 |
baseline [23] | 76.48 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
Suqiang Ma
et al.
Remote Sensing,
2022
Wisal Khan
et al.
Symmetry,
2022
Ruoqi Wei
et al.
Entropy,
2021
© 2024 MDPI (Basel, Switzerland) unless otherwise stated