I would like to know if it is possible to use Token Labeling to achieve scores higher than that of the annotator model, I believe this was the case with VOLO D5 model where it achieved higher score than NFNet, model used for annotation.
Yes, you can also refer to Figure 4 (Right) in our paper for more results. The performance of the model is related to its capacity as well as the accuracy of the annotator model.
Greetings,
Thank you for this incredible research.
I would like to know if it is possible to use Token Labeling to achieve scores higher than that of the annotator model, I believe this was the case with VOLO D5 model where it achieved higher score than NFNet, model used for annotation.