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 …

Prevalent semantic segmentation solutions, despite their different network designs (FCN
based or attention based) and mask decoding strategies (parametric softmax based or pixel …

ImageNet-1K serves as the primary dataset for pretraining deep learning models for
computer vision tasks. ImageNet-21K dataset, which is bigger and more diverse, is used …

Self-supervised learning algorithms based on instance discrimination train encoders to be
invariant to pre-defined transformations of the same instance. While most methods treat …

Recent self-supervised methods for image representation learning are based on maximizing
the agreement between embedding vectors from different views of the same image. A trivial …

Contrastive learning has become a key component of self-supervised learning approaches
for computer vision. By learning to embed two augmented versions of the same image close …

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

Deep supervised learning has achieved great success in the last decade. However, its
defects of heavy dependence on manual labels and vulnerability to attacks have driven …

Being able to learn dense semantic representations of images without supervision is an
important problem in computer vision. However, despite its significance, this problem …

Recently, self-supervised learning methods like MoCo, SimCLR, BYOL and SwAV have
reduced the gap with supervised methods. These results have been achieved in a control …