Subhankar Roy

Where to use dropout in Resnets?

1

Hi, Thanks for sharing the code for your paper. Could you please tell me where I must use the dropout layers in a resnet50 for a classification task on 224x224...

Non parametric grouping

1

Hi, Can you please provide more details as how you do the non-parametric grouping on CLIP's features (obtained from ViT encoder)?

Hi, Thanks for sharing the code. Can you please make available the config files for the resnet experiments?

Clarification on evaluation metric M-IoU

1

Hi Fabio, I would like to ask how do you compute the final M-IoU in the tables. In the table below I see that to compute the **Old** and **All**...

Hi, thanks for sharing the code. Do you think this code can be adapted to classify images, given the features input the GCN is obtained from a resnet50 encoder?

Hi, kindly add this **CoLLAs 2023** paper titled **RaSP: Relation-aware Semantic Prior for Weakly Supervised Incremental Segmentation**. This paper addresses class-incremental semantic segmentation under the assumption that only *image-level* labels...

Hi, great work, waiting for the code release. I have a naive question regarding the network latency. While the event cameras have very low latency in data acquisition when compared...