AudioSet) has an even larger negative impact.

The learnt models in the latter domain can then be used for a diverse set of tasks in a zero-shot way, similar to "Contrastive Language-Image

The code is available at Contrastive-Sampling .

Contrastive learning has recently emerged as a promising approach for learning data representations that discover and disentangle the explanatory factors of the data.

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.

However, there still exist many properties of contrastive learning that are not guaranteed.

Such a lack of alignment and uniformity might restrict the transferability and robustness of embeddings. To this end, we devise a new fine-tuning method for robust representation equipping better alignment and uniformity. First, we propose a Geodesic Multi-Modal Mixup that mixes the embeddings of image and text to generate hard negative samples on the hypersphere.