SAM3-LiteText: An Anatomical Study of the SAM3 Text Encoder for Efficient Vision-Language Segmentation
Paper
• 2602.12173 • Published
• 1
Model Card for SAM3-LiteText (MobileCLIP text encoder)
This is a Transformers-compatible checkpoint of the SAM3-LiteText paper.
Usage is identical to SAM-3 in Transformers.
PR is here: https://github.com/huggingface/transformers/pull/44320.
- Downloads last month
- 57
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support