amr younis
ermac1987
AI & ML interests
Follow me on other social networks for updates about the AI Comic Factory, Atryon, AI Tube.. and more!
Recent Activity
updated
a collection
14 days ago
tool magical
liked
a Space
14 days ago
ByteDance/InfiniteYou-FLUX
reacted
to
prithivMLmods's
post
with ๐ค
14 days ago
Dropping Downstream tasks using newly initialized parameters and weights ([classifier.bias & weights]) support domain-specific ๐ถ๐บ๐ฎ๐ด๐ฒ ๐ฐ๐น๐ฎ๐๐๐ถ๐ณ๐ถ๐ฐ๐ฎ๐๐ถ๐ผ๐ป. Based on siglip2-base-patch16-224 and DomainNet (single-domain, multi-source adaptation), with Fashion-MNIST & More for experimental testing. ๐งคโ๏ธ
Fashion-Mnist : https://huggingface.co/prithivMLmods/Fashion-Mnist-SigLIP2
Mnist-Digits : https://huggingface.co/prithivMLmods/Mnist-Digits-SigLIP2
Multisource-121 : https://huggingface.co/prithivMLmods/Multisource-121-DomainNet
Painting-126 : https://huggingface.co/prithivMLmods/Painting-126-DomainNet
Sketch-126 : https://huggingface.co/prithivMLmods/Sketch-126-DomainNet
Clipart-126 : https://huggingface.co/prithivMLmods/Clipart-126-DomainNet
Models are trained with different parameter settings for experimental purposes only, with the intent of further development. Refer to the model page below for instructions on running it with Transformers ๐ค.
Collection : https://huggingface.co/collections/prithivMLmods/domainnet-0324-67e0e3c934c03cc40c6c8782
Citations : SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features https://arxiv.org/pdf/2502.14786 & Moment Matching for Multi-Source Domain Adaptation : https://arxiv.org/pdf/1812.01754
Organizations
None yet
Collections
1
spaces
1
models
1
datasets
None public yet