In this paper, we dive deeper into this class of strategies.

In the supplementary material, we first introduce the pseudo algorithm of DA W . Then we clarify the Then, we provide a more detailed explanation of Figures 1, 2, 4, and 5, which are slightly abbreviated due to the limited space of the main paper. In the naive pseudo-labeling method, all pseudo labels are enrolled into training, i.e., E 1 + E 2, which is guaranteed by theoretical functional analysis in the next section. Inequality 45 holds true at all times. In this section, we provide more qualitative results between ours and other competitors.

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.

The proposed indicators adequately measure the effectiveness of the soft labels generated in this process.

One may naturally ask, "When would these explanations be helpful?"

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.