Audio-visual learning has been a major pillar of multi-modal machine learning, where the community mostly focused on its modality-aligned setting, i.e ., the

Despite its popularity, self-training is well-believed to be unreliable and often leads to training instability.

Vision-language pre-training methods, e.g., CLIP, demonstrate an impressive zero-shot performance on visual categorizations with the class proxy from the text embedding of the class name.

Additionally, prompt-based FT with the PCP outperforms state-of-the-art semi-supervised approaches with greater simplicity, eliminating the need for an iterative process and extra data augmentation. Our further analysis explores the performance lower bound of the PCP and reveals that the advantages of PCP persist across different sizes of models and datasets.

Few-shot classification (FSC) is challenging due to the scarcity of labeled training data (e.g.