EVA-CLIP: Improved Training Techniques for CLIP at Scale
TL
TL;DR
This paper proposes a series of models that significantly improve the efficiency and effectiveness of CLIP training, and incorporates new techniques for representation learning, optimization, and augmentation, enabling EVA-CLIP to achieve superior performance compared to previous CLIP models with the same number of parameters but significantly smaller training costs.
Abstract
Contrastive language-image pre-training, CLIP for short, has gained increasing attention for its potential in various scenarios. In this paper, we propose EVA-CLIP, a series of models that significantly improve the efficiency and effectiveness of CLIP training. Our approach incorporates new techniques for representation learning, optimization, and augmentation, enabling EVA-CLIP to achieve superior performance compared to previous CLIP models with the same number of parameters but significantly smaller training costs. Notably, our largest 5.0B-parameter EVA-02-CLIP-E/14+ with only 9 billion seen samples achieves 82.0 zero-shot top-1 accuracy on ImageNet-1K val. A smaller EVA-02-CLIP-L/14+ with only 430 million parameters and 6 billion seen samples achieves 80.4 zero-shot top-1 accuracy on ImageNet-1K val. To facilitate open access and open research, we release the complete suite of EVA-CLIP to the community at https://github.com/baaivision/EVA/tree/master/EVA-CLIP.
References52 items
1
EVA-02: A Visual Representation for Neon Genesis
2
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
3
Scaling Language-Image Pre-Training via Masking
4
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
5