Hugging Face's logo

google
/
siglip2-base-patch16-384

Zero-Shot Image Classification
Transformers
Safetensors
siglip
vision
Model card Files Community
3

What parameters are fine-tuned for siglip2 using catseg's line for Open-Vocabulary semantic segmentation in this paper?

#3
by xiaoqing111 - opened
Discussion
xiaoqing111

What parameters are fine-tuned for siglip2 using catseg's line for Open-Vocabulary semantic segmentation in this paper?

mitsch

See https://github.com/google-research/big_vision/issues/171

Sign up or log in to comment