Closed truetone2022 closed 1 year ago
Here are some other experiments we did. The Swin-Base* in this table is based on the ImageNet-22K with 224x224 resolution.
Thanks! Furthermore, I wonder why the QAHOI with R50 backbone cannot surpass the QPIC with R50 backbone? Intuitively, deformable-detr-r50 should perform better than detr-r50 on HICO-DET dataset
Both of them are fine-tuned on COCO, but QAHOI cannot acquire a huge performance boost like QPIC, it's strange.
epoch | AP | AP-S | AP-M | AP-L | |
---|---|---|---|---|---|
Deformable DETR | 50 | 44.5 | 27.1 | 47.6 | 59.6 |
DETR | 500 | 42.0 | 20.5 | 45.8 | 61.1 |
We use the deformable-detr-r50 trained 50 epochs on COCO.
I think there are three main reasons that QAHOI-r50-fine is lower that QPIC-r50-fine:
If you have any ideas, feel free to point them out.
Very thanks for your helpful reply!
Have you tried to train the QAHOI which is based on the ImageNet-22K 224x224 pre-trained swin transformer backbone?