Self-supervised learning based on instance discrimination has shown remarkable progress.
In particular, contrastive learning, which regards each image as well as its augmentations as …

Unsupervised image representations have significantly reduced the gap with supervised
pretraining, notably with the recent achievements of contrastive learning methods. These …

The ubiquity of camera-enabled devices has led to large amounts of unlabeled image data
being produced at the edge. The integration of self-supervised learning (SSL) and federated …

Recently the state space models (SSMs) with efficient hardware-aware designs, ie, the
Mamba deep learning model, have shown great potential for long sequence modeling …

Learning representations of images that are invariant to sensitive or unwanted attributes is
important for many tasks including bias removal and cross domain retrieval. Here, our …

Mixup is a well-known data-dependent augmentation technique for DNNs, consisting of two
sub-tasks: mixup generation and classification. However, the recent dominant online training …

Contrastive self-supervised learning has outperformed supervised pretraining on many
downstream tasks like segmentation and object detection. However, current methods are …

Non-contrastive methods of self-supervised learning (such as BYOL and SimSiam) learn
representations by minimizing the distance between two views of the same image. These …

Self-supervised representation learning approaches have recently surpassed their
supervised learning counterparts on downstream tasks like object detection and image …

We launch EVA, a vision-centric foundation model to explore the limits of visual
representation at scale using only publicly accessible data. EVA is a vanilla ViT pre-trained …