With the urgent demand for generalized deep models, many pre-trained big models are
proposed, such as bidirectional encoder representations (BERT), vision transformer (ViT) …

This paper presents a simple yet effective framework MaskCLIP, which incorporates a newly
proposed masked self-distillation into contrastive language-image pretraining. The core idea …

Abstract Contrastive Language-Image Pre-training (CLIP) has significantly boosted the
performance of various vision-language tasks by scaling up the dataset with image-text pairs …

Although an object may appear in numerous contexts, we often describe it in a limited
number of ways. Language allows us to abstract away visual variation to represent and …

Large-scale vision-language pre-training has achieved promising results on downstream
tasks. Existing methods highly rely on the assumption that the image-text pairs crawled from …

Contrastive pre-training of image-text foundation models such as CLIP demonstrated
excellent zero-shot performance and improved robustness on a wide range of downstream …

Generating textual descriptions from visual inputs is a fundamental step towards machine
intelligence, as it entails modeling the connections between the visual and textual …

Recent advances in zero-shot image recognition suggest that vision-language models learn
generic visual representations with a high degree of semantic information that may be …

Contrastive learning-based vision-language pre-training approaches, such as CLIP, have
demonstrated great success in many vision-language tasks. These methods achieve cross …

The success of large-scale contrastive vision-language pretraining (CLIP) has benefited
both visual recognition and multimodal content understanding. The concise design brings …