barebell / da Goto Github PK

Hello,

Are you still updating this repo?

Hi,

The repository is very impressive. Can you please add my new IEEE Transactions on Multimedia article on open-set DA in your repository?

Title: Adversarial Network with Multiple Classifiers for Open Set Domain Adaptation
Authors: Tasfia Shermin, Guojun Lu, Shyh Wei Teng, Manzur Murshed, Ferdous Sohel
Publisher: IEEE TMM
Year: 2020
Code: https://github.com/tasfia/DAMC

Regards,
Tasfia

Generally, my problem is about predicting facial expression from a facial image (think of the classification of emotion like happy/sad/angry/etc).
The source domain is very accurately labeled. The image comes from a frontal camera.
The target domain I do not have any labels. The image has different lighting from the environment and a slightly different camera angle.
Do you have a suggestion of a method to help me classify the target domain as accurately as possible? I do not care about accuracy for the source domain though.

What application have you used unsupervised domain adaptation for in the past?

hi @barebell
Please add the following paper related to Domain Adaptation accepted at IJCNN 2019
Paper: https://arxiv.org/abs/1904.01341
Project page: https://vinodkkurmi.github.io/DiscriminatorDomainAdaptation/

Thanks

hi @barebell, Is this paper accepted for ICML
Simple Domain Adaptation with Class Prediction Uncertainty Alignment?
Because I coudn't find it in ICML webpage. Can you please share the source for the same. It will useful for us to cite. Thanks

Hi,

Could you please add our new work into this list? The paper is about Unsupervised Domain Adaptation via Disentangled Representations.

You could find the paper here: https://arxiv.org/abs/1907.13590

Best,
Junlin

hi @barebell
Please add the following paper related to Domain Adaptation accepted at BMVC 2019
Paper: https:https://arxiv.org/abs/1907.10628
Project page: https://delta-lab-iitk.github.io/CD3A/

Thanks

I'd like to identify whether the new data is in a known class by the neural network , do you have any papers to recommend?

Hello,
thank you for your work. Could you please add this paper to your repo?
Title: An unsupervised domain adaptation scheme for single-stage artwork recognition in cultural sites
Code: https://github.com/fpv-iplab/DA-RetinaNet
Journal Image and Vision Computing: https://www.sciencedirect.com/science/article/abs/pii/S0262885621000032?dgcid=rss_sd_all