Debasmit Das

Performance on Vanilla GAN ?

2

Did you trying using the Vanilla GAN before using W-GAN ? I tried your approach using Vanilla GAN on toy 2D data and it does not work and wanted to...

CASIA Anti-spoofing Database

2

Any idea how to obtain the CASIA dataset ? The publicly available link seems to be broken.

Pipeline for processing Videos of anti-spoofing dataset ?

1

I see that all the datasets are available in Video format. Is there any code/pipeline you use to process the database into images ?

I have been trying to measure the GMACs and params of YOLACT using the thop model. Unfortunately it returns an error when using the following script: ``` net = Yolact()...

References - [1] https://www.sciencedirect.com/science/article/abs/pii/S0952197618301088 [2] https://ieeexplore.ieee.org/abstract/document/8451152 [3] https://link.springer.com/chapter/10.1007/978-3-030-01424-7_34

Since the ADE 20K dataset contains both indoor and outdoor scenes, is is possible to train the ADE20K on only indoor scenes ? Is there any way to filter out...

Hi, What parameters did you use to produce the t-SNE plot i.e. Figure 3 in the Appendix of https://arxiv.org/pdf/1703.05175.pdf

In the tables, you compare all the methods in the conventional and generalized setting. So, is there any way to measure the statistical significance of pairs of methods ? In...

Hyper-parameter selection ?

1

It seems that the reverse validation (rv) approach (as mentioned in the paper) to hyper-parameter selection has not been carried out in the repository. So I wanted to ask some...

Implementation of metrics in the Dreambooth paper

1

Is there an implementation of the evaluation metrics used in the Dreambooth paper like subject fidelity, prompt fidelity, DINO, CLIP-I and CLIP-T ?