EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters
This work provides a powerful open-source CLIP model to facilitate research in vision and multimodal AI, though it is incremental in scaling an existing paradigm.
The authors tackled scaling contrastive language-image pretraining (CLIP) by developing EVA-CLIP-18B, an 18-billion parameter model that achieves 80.7% zero-shot top-1 accuracy across 27 benchmarks, outperforming previous open-source models.
Scaling up contrastive language-image pretraining (CLIP) is critical for empowering both vision and multimodal models. We present EVA-CLIP-18B, the largest and most powerful open-source CLIP model to date, with 18-billion parameters. With only 6-billion training samples seen, EVA-CLIP-18B achieves an exceptional 80.7% zero-shot top-1 accuracy averaged across 27 widely recognized image classification benchmarks, outperforming its forerunner EVA-CLIP (5-billion parameters) and other open-source CLIP models by a large margin. Remarkably, we observe a consistent performance improvement with the model size scaling of EVA-CLIP, despite maintaining a constant training dataset of 2-billion image-text pairs from LAION-2B and COYO-700M. This dataset is openly available and much smaller than the in-house datasets (e.g., DFN-5B, WebLI-10B) employed in other state-of-the-art CLIP models. EVA-CLIP-18B demonstrates the potential of EVA-style weak-to-strong visual model scaling. With our model weights made publicly available, we hope to facilitate future research in vision and multimodal foundation models.