single mention · model architecture
Fused SigLIP-DINOv2 vision encoder
Combines SigLIP and DINOv2 encoders into a fused vision backbone.
The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See multimodal architecture for the methods filed beside it.
Also called Fused SigLIP-DinoV2 dual vision encoder, dual vision encoder.
Filed under model architecture › multimodal architecture