Meet the team that turns your ideas into work.

Discover EightBots
EIGHTBOTS
Contact salesSign up
rinnaJapanese image-text encoders

Japanese CLIP ViT-B/16

Japanese CLIP ViT-B/16 learns shared image and Japanese-text representations through contrastive image-text training.

Japanese captions train the shared space

The training set is CC12M with captions translated into Japanese. The published release date is 12 May 2022. The weights are encoders for image-text comparison, not an image generator.Japanese CLIP ViT-B/16 official model card

Evaluate retrieval with Japanese queries

Practical guidance. Compare Japanese query phrases that describe the same image in different words. Similarity rankings can change with phrasing. A high score measures alignment in the learned space; it is not a factual caption.

Specifications & access

Japanese CLIP ViT-B/16 specifications
DetailValue and conditions
Launch date
AccessDownloadable
Model identifiersjapanese-clip-vit-b-16
ArchitectureViT-B/16 image encoder with a 12-layer BERT text encoder.Japanese CLIP ViT-B/16 official model card
AncestryThe image encoder starts from AugReg vit-base-patch16-224.Japanese CLIP ViT-B/16 official model card
LicenseApache 2.0.Japanese CLIP ViT-B/16 official model card

Related models

  • Japanese CLOOB ViT-B/16

    rinna ยท Japanese image-text encoders

    Japanese CLOOB ViT-B/16 learns shared image and Japanese-text representations through Contrastive Leave One Out Boost training.

    Launch date Downloadable