ACVSA

@wenguanwang @tfzhou Thank you for your excellent contributions, can you please tell me if the paper code only provides profiles for prototype learning on the Cityscapes dataset?

Hello, thank you for your excellent work, I would like to ask what are the two values returned in the code by sink_horn, what do q and indexes mean respectively?

您好，我想复现的是基于backbone是resnet50条件下，mcibi++在Cityscapes数据集上的结果，在配置文件为configs/base_config.py中第84行将context_within_image的is_on设置为false，并且在configs/memorynetv2/memorynetv2_resnet50os8_cityscapes.py中也没有配置is_on为True,但我发现其他的配置文件中将is_on重新设置为True,可以帮我解答一下嘛

您好，我还有个问题，我没有找到FCN+MCIBI++的配置文件，好像只有ASPP,PPM,UPERNET+MCIBI++的配置文件

不好意思，之前我看错了，我还有个问题，就是你代码的modules/models/segmentors/memorynet/memory.py中的第214行代码，这个relation和argmax对应的变量是什么意思呀，可以为我解答一下嘛，谢谢您。 ` assert strategy in ['cosine_similarity'] # ----(K, C) * (C, num_feats_per_cls) --> (K, num_feats_per_cls) relation = torch.matmul( F.normalize(feats_cls, p=2, dim=1), F.normalize(self.memory[clsid].data.permute(1, 0).contiguous(), p=2, dim=0), ) argmax = relation.argmax(dim=1)# 返回最大值的索引...

您好，我也非常想知道论文中的图3的两个Structure map是如何通过代码得到的。

Thank you for the contributions of the DINOv3 team. May I ask if it is possible to release the weights of the segmentation head and depth prediction head adapted for...