Hello @ycliu93, Thank you for sharing awesome work!
I have question about the performance of PASCAL VOC(uploaded model weight that using voc07 as labeled data and voc12 as unlabeled data)
When i check the performance(AP, AP50) of uploaded PASCAL VOC model weight with cocoEVAL, the AP is lower than the result that reported in the paper(paper -> AP: 48.7, AP50: 77.4 / uploaded model weight -> AP: 45.2, AP50:72.2)
Is it because of the small batch size? or is there any other issue?
Since some works(i.e. Instant Teaching) achieve similar performance(AP: 48.7, AP50:78.3) using only EMA and strong augmentation with small batch size(label:8, unlabel:8), i think that there could be other issue.
Last row is reimplementation result based on your repository.
Reimplementation result also shows similar performance.
Hello @ycliu93, Thank you for sharing awesome work!
I have question about the performance of PASCAL VOC(uploaded model weight that using voc07 as labeled data and voc12 as unlabeled data)
When i check the performance(AP, AP50) of uploaded PASCAL VOC model weight with cocoEVAL, the AP is lower than the result that reported in the paper(paper -> AP: 48.7, AP50: 77.4 / uploaded model weight -> AP: 45.2, AP50:72.2)
Is it because of the small batch size? or is there any other issue?
Since some works(i.e. Instant Teaching) achieve similar performance(AP: 48.7, AP50:78.3) using only EMA and strong augmentation with small batch size(label:8, unlabel:8), i think that there could be other issue.
Last row is reimplementation result based on your repository. Reimplementation result also shows similar performance.
Thank you!