specific method · not yet filed
contrastive pre-training of vision encoder
Also called contrastive pre-training.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
During contrastive pretraining, we optimize the model using the sigmoid contrastive loss introduced by SigLIP (Zhai et al., 2023) on approximately 47B image-text pairs sourced from alt-text data.
usedunclearin DeepSeek-V4.1-FlashDeepSeek