Abstract Pretrained Foundation Models (PFMs) are regarded as the foundation for various
downstream tasks across different data modalities. A PFM (eg, BERT, ChatGPT, GPT-4) is …

Deep supervised learning algorithms typically require a large volume of labeled data to
achieve satisfactory performance. However, the process of collecting and labeling such data …

The recent breakthroughs in natural language processing for model pretraining on large
quantities of data have opened the way for similar foundation models in computer vision …

Abstract Contrastive Language-Image Pre-training (CLIP) achieves promising results in 2D
zero-shot and few-shot learning. Despite the impressive performance in 2D, applying CLIP …

Abstract We present Masked Feature Prediction (MaskFeat) for self-supervised pre-training
of video models. Our approach first randomly masks out a portion of the input sequence and …

This paper presents SimMIM, a simple framework for masked image modeling. We have
simplified recently proposed relevant approaches, without the need for special designs …

Abstract We propose Masked Siamese Networks (MSN), a self-supervised learning
framework for learning image representations. Our approach matches the representation of …

We present a novel masked image modeling (MIM) approach, context autoencoder (CAE),
for self-supervised representation pretraining. We pretrain an encoder by making predictions …

Abstract Contrastive Language-Image Pre-training (CLIP) has made a remarkable
breakthrough in open-vocabulary zero-shot image recognition. Many recent studies …

Vision-language representation learning largely benefits from image-text alignment through
contrastive losses (eg, InfoNCE loss). The success of this alignment strategy is attributed to …