🛠️ Steven Gong

Search

SearchSearch

May 09, 2025, 1 min read

CLIP

Sigmoid Loss for Language Image Pre-Training (SigLIP)

SigLIP is an improved version of CLIP which introduces sigmoid-based Contrastive Loss instead of the traditional softmax-based contrastive loss used in CLIP.

Resources

  • https://arxiv.org/pdf/2303.15343
  • https://huggingface.co/docs/transformers/en/model_doc/siglip

Graph View

Backlinks

  • Contrastive Language-Image Pre-Training (CLIP)
  • OpenVLA

Created with Quartz, © 2025

  • Blog
  • LinkedIn
  • Twitter
  • GitHub