BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

🤖 Plain-English Summary

The cost of vision-and-language pre-training has become increasingly prohibitive due to end-to-end training of large-scale models. For example, our model outperforms Flamingo80B by 8.7% on zero-shot VQAv2 with 54x fewer trainable parameters.

🔑 Key Findings

• This paper proposes BLIP-2, a generic and efficient pre-training strategy that bootstraps vision-language pre-training from off-the-shelf frozen pre-trained image encoders and frozen large language models.
• BLIP-2 bridges the modality gap with a lightweight Querying Transformer, which is pre-trained in two stages.
• The first stage bootstraps vision-language representation learning from a frozen image encoder.

🔗 Related Resources