Several studies have attempted to reduce the number of image-text pairs used for vision-language pre-training.

Under this setting, previous SSL methods tend to predict wrong pseudo-labels with the model fitted on labeled data, resulting in noise accumulation.

However, zero-shot learning methods still require human instruction set to solve a new task.

While several previous works have focused on classifying close-set samples and detecting open-set samples during testing, it's still essential to be able to classify unknown subjects as human beings.

Visual and auditory perception is crucial for observing the world. When we hear a sound, our brain will extract semantic information and locate the sounding source.

However, generative models have rarely been considered for semi-supervised classification recently.