In this paper, we present a novel approach termed Prompt-Driven Feature Diffusion (PDFD) within a semi-supervised learning framework for Open World Semi-Supervised Learning (OW-SSL). At its core, PDFD deploys an efficient feature-level diffusion model with the guidance of class-specific prompts to support discriminative feature representation learning and feature generation, tackling the challenge of the non-availability of labeled data for unseen classes in OW-SSL. In particular, PDFD utilizes class prototypes as prompts in the diffusion model, leveraging their class-discriminative and semantic generalization ability to condition and guide the diffusion process across all the seen and unseen classes. Furthermore, PDFD incorporates a class-conditional adversarial loss for diffusion model training, ensuring that the features generated via the diffusion process can be discriminatively aligned with the class-conditional features of the real data. Additionally, the class prototypes of the unseen classes are computed using only unlabeled instances with confident predictions within a semi-supervised learning framework. We conduct extensive experiments to evaluate the proposed PDFD. The empirical results show PDFD exhibits remarkable performance enhancements over many state-of-the-art existing methods.

本文提出了一种新颖的方法，称为Prompt-Driven Feature Diffusion (PDFD)，在半监督学习框架下用于开放世界半监督学习 (OW-SSL)。该方法利用类原型作为提示，在扩散模型中引导扩散过程，以支持有鉴别特征表示学习和特征生成的效率和准确性，从而解决OW-SSL中无法获得未知类别标记数据的挑战。此外，PDFD还结合了类条件对抗性损失以确保扩散过程中生成的特征可以与真实数据的类条件特征进行有鉴别性的对齐。通过大量实验证明，PDFD相比于许多现有的先进方法取得了显著的性能提升。

基于提示驱动的特征传播用于开放式半监督学习