论文标题
迅速分发学习
Prompt Distribution Learning
论文作者
论文摘要
我们提出了迅速的分发学习，以有效地调整预先训练的视觉语言模型以解决下游识别任务。我们的方法不仅从几个样本中学习了低偏差的提示，而且还捕获了各种提示的分布以处理不同的视觉表示。这样，我们提供了与任务相关的高质量内容，以促进识别。这种提示分发学习是通过一种有效的方法来实现的，该方法可以学习提示的输出嵌入而不是输入嵌入。因此，我们可以采用高斯分布来有效地对其进行建模，并为有效的训练提供替代损失。在12个数据集上进行的广泛实验表明，我们的方法始终如一，显着优于现有方法。例如，与人工制作的提示相比，每个类别有1个样本，相对将平均结果提高了9.1％。
We present prompt distribution learning for effectively adapting a pre-trained vision-language model to address downstream recognition tasks. Our method not only learns low-bias prompts from a few samples but also captures the distribution of diverse prompts to handle the varying visual representations. In this way, we provide high-quality task-related content for facilitating recognition. This prompt distribution learning is realized by an efficient approach that learns the output embeddings of prompts instead of the input embeddings. Thus, we can employ a Gaussian distribution to model them effectively and derive a surrogate loss for efficient training. Extensive experiments on 12 datasets demonstrate that our method consistently and significantly outperforms existing methods. For example, with 1 sample per category, it relatively improves the average result by 9.1% compared to human-crafted prompts.
