An important goal of self-supervised learning is to enable model pre-tra...
Masked image modeling (MIM) learns representations with remarkably good
...
Masked image modeling (MIM) as pre-training is shown to be effective for...
Image classification, which classifies images by pre-defined categories,...
This paper presents SimMIM, a simple framework for masked image modeling...
We present techniques for scaling Swin Transformer up to 3 billion param...
We are witnessing a modeling shift from CNN to Transformers in computer
...
Contrastive learning methods for unsupervised visual representation lear...
This paper presents parametric instance classification (PIC) for unsuper...
In the feature maps of CNNs, there commonly exists considerable spatial
...
The convolution layer has been the dominant feature extractor in compute...