Web-crawled pretraining datasets underlie the impressive" zero-shot" evaluation
performance of multimodal models, such as CLIP for classification and Stable-Diffusion for …

The popular CLIP model displays impressive zero-shot capabilities thanks to its seamless
interaction with arbitrary text prompts. However, its lack of spatial awareness makes it …

Audio-visual zero-shot learning methods commonly build on features extracted from pre-
trained models eg video or audio classification models. However existing benchmarks …

Knowledge distillation (KD) is the de facto standard for compressing large-scale models into
smaller ones. Prior works have explored ever more complex KD strategies involving different …

Contrastive vision-language models like CLIP have gained popularity for their versatile
applicable learned representations in various downstream tasks. Despite their successes in …

Learning representations that generalize under distribution shifts is critical for building
robust machine learning models. However, despite significant efforts in recent years …

Out-of-Domain (OOD) generalization is the ability of a model trained on one or more
domains to generalize to unseen domains. In the ImageNet era of computer vision …

Severe data imbalance naturally exists among web-scale vision-language datasets. Despite
this, we find CLIP pre-trained thereupon exhibits notable robustness to the data imbalance …

Multi-modal contrastive learning with language supervision has presented a paradigm shift
in modern machine learning. By pre-training on a web-scale dataset, multi-modal contrastive …

Early in life and without special training, human beings discern resemblance between
abstract visual stimuli, such as drawings, and the real-world objects they represent. We used …