Minami

Results 8 issues of Minami

ViT family show strong robustness on RandomDrop and Domain shift Problem. The thing is , I 'm working on object detection these days,detr is an end to end object detection...

![image](https://user-images.githubusercontent.com/38450078/198572106-f41583db-47d2-4fca-8809-bbb9f95f56bc.png) I download your dataset,then change nothing in the code.But when it come to 82 epoch, the AP of holothurian is still have something wrong

My card cannot support your code, so I want to use yolov7 to run your dataset,but it's weird that YOLOV7 reach a very low mAP, just about mAP50 = 30,even...

![image](https://user-images.githubusercontent.com/38450078/221599751-cdf801ed-0abd-4f76-affc-617ee2715893.png) I want to know how to do fine-tune?It's just use source domain FSD as a pre-train model,and start faster rcnn again?Maybe it will lead to catastrophic forgetting according to...

![3a85e76236fe5a5cc0ed6ba419ee9e4](https://github.com/mil-tokyo/dg_mmld/assets/38450078/110d837e-1bc5-49a3-84ab-cf9049255dd6) I don't know what is the size of pseudo domain label.Where is the corrsponding code? Thank you

Could you please share how you applied the CLIP initialization to the ori RN101? Could you also let me know where I can find the corresponding code?

In section 4.2 Implementation Details :"We initialize the detector with CLIP pre-trained weights" I can't find the code position