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.

EVA-CLIP-18B 是目前最大且最强大的开源 CLIP 模型，拥有 180 亿参数；只看到 60 亿个训练样本，EVA-CLIP-18B 在 27 个广泛公认的图像分类基准中，以异乎寻常的 80.7% 零示例一级准确度表现出色，在模型大小扩展方面，观察到 EVA-CLIP 的持续性能改进；希望通过提供我们的模型权重公开，促进未来在视觉和多模态基础模型方面的研究。

EVA-CLIP-18B：扩展到 180 亿参数的 CLIP

EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters

We introduce a principled approach for unsupervised structure learning of
deep neural networks. We propose a new interpretation for depth and inter-layer
connectivity where conditional independencies in the input distribution are
encoded hierarchically in the network structure. Thus, the depth of the network
is determined inherently. The proposed method casts the problem of neural
network structure learning as a problem of Bayesian network structure learning.
Then, instead of directly learning the discriminative structure, it learns a
generative graph, constructs its stochastic inverse, and then constructs a
discriminative graph. We prove that conditional-dependency relations among the
latent variables in the generative graph are preserved in the class-conditional
discriminative graph. We demonstrate on image classification benchmarks that
the deepest layers (convolutional and dense) of common networks can be replaced
by significantly smaller learned structures, while maintaining classification
accuracy---state-of-the-art on tested benchmarks. Our structure learning
algorithm requires a small computational cost and runs efficiently on a
standard desktop CPU.

本文提出一种基于贝叶斯网络结构学习的方法，用于无监督结构学习深度神经网络，通过生成图，构建其随机反向，然后构建一个判别图，证明生成图的潜变量之间的条件依赖关系在条件 “分类条件下” 丢失在判别图，从而实现通用网络深层（卷积和密集）的学习结构替代，在保持分类准确性的同时显著减少计算成本。