Best Alternatives to CoCa: Contrastive Captioners are Image-Text Foundation Models (CoCa)
1 alternatives ranked by real usage data. CoCa: Contrastive Captioners are Image-Text Foundation Models (CoCa) scores 20/100 — 1 tool score higher.
* ⭐ 05/2022: [VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts (VLMo)](https://arxiv.org/abs/2111.02358)
20
1 alternatives
1 free options
1 score higher