Yabin Zhang comments

Results 7 comments of


                                            Yabin Zhang

visda2017 accuracy

Same problem +1

The information about training data

Is there any plan to release the training data, e.g., "several million 3D models"? If not, could you suggest how these training samples are collected? Thanks~

I can not find the discriminator in your code .

The tensor product is implemented in the line [ 238 ] of [ https://github.com/YabinZhang1994/CDAN-re-implement/blob/master/models/resnet.py ].

test dataset

Am I correct to use part of source target for validation set for weights update ? --> I am not certain since I do not fully understand your question. How...

test dataset

Ok, I see. The current code base does not support three streams of input: labeled source data, labeled source data, and unlabeled source data. My suggestion is to add another...

Inquiry About DMN Reproduction: Gap Between Paper Results (Table 3) and GitHub Logs

Thanks for your comments. 1. Not yet. However, we conducted experiments on ImageNet and observed very small fluctuations with different seeds, as presented in the paper. 2. No specific data...

Reproducibility of “Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models”

Thanks for your interest. All components are released. You can easily reproduct our results with the code.