利用类别名称提升视觉-语言模型的小样本分类性能
Exploiting Category Names for Few-Shot Classification with Vision-Language Models
AI总结：
本文提出用类别名称初始化视觉-语言模型分类头，以弥合大参数量与小样本数据间的差距，并在多个五样本图像分类基准上取得最先进结果。
摘要：
在大规模数据上预训练的视觉-语言基础模型为许多视觉理解任务提供了强大工具。值得注意的是，许多视觉-语言模型构建了两个编码器（视觉编码器和文本编码器），能够将两种模态映射到同一嵌入空间。因此，所学表征在图像分类等任务上取得了良好的零样本性能。然而，当每个类别仅有少量示例时，大型视觉-语言模型的潜力往往未能充分发挥，这主要是由于大量参数与相对较少的训练数据之间存在差距。本文表明，通过利用类别名称初始化分类头，可以显著提升小样本分类性能。借助所提出的类别名称初始化方法，我们的模型在多个小样本图像分类基准上取得了最先进性能（例如，在 ImageNet 上达到 87.37%，在 Stanford Cars 上达到 96.08%，二者均采用五样本学习）。
英文摘要：
Vision-language foundation models pretrained on large-scale data provide a powerful tool for many visual understanding tasks. Notably, many vision-language models build two encoders (visual and textual) that can map two modalities into the same embedding space. As a result, the learned representations achieve good zero-shot performance on tasks like image classification. However, when there are only a few examples per category, the potential of large vision-language models is often underperformed, mainly due to the gap between a large number of parameters and a relatively small amount of training data. This paper shows that we can significantly improve the performance of few-shot classification by using the category names to initialize the classification head. With the proposed category name initialization method, our model obtains the state-of-the-art performance on a number of few-shot image classification benchmarks (e.g., 87.37% on ImageNet and 96.08% on Stanford Cars, both using five-shot learning).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
