Abstract" A picture is worth a thousand words", significantly beyond mere a categorization.
Accompanied by that, many patches of the image could have completely irrelevant …

Despite deep learning's widespread success, its data-hungry and computationally
expensive nature makes it impractical for many data-constrained real-world applications …

Visual-language models based on CLIP have shown remarkable abilities in general few-
shot image classification. However, their performance drops in specialized fields such as …

In recent years, patch-based approaches have shown promise in few-shot learning, with
further improvements observed through the use of self-supervised learning. However, we …

Here, we show that the InfoNCE objective is equivalent to the ELBO in a new class of
probabilistic generative model, the recognition parameterised model (RPM). When we learn …