Jiangpengtao

Results 8 comments of Jiangpengtao

Thanks! I will add our method and send you a Pull Request!

@jbeomlee93, I have the same request. Could you provide the deeplab-pytorch code for MS COCO? I want to know the hyper-parameters in your experiments.

你好,有不同层的cam图和实验细节吗? 可以发我邮箱,我先看下。

Hello, they all come from the deeplab webpage.

@Zhengyang1995 Yes, the resnet is pretrained for classification on MS-COCO. The vgg is pretrained for classification on ImageNet (We don't use the pretrained model on COCO for vgg).

What do you mean by the AUC values?

Hello, I also utilize the clip model to classify the masks from SAM. However, I find the performance is poor. Increasing the image size of the clip model may improve...