Yanbin Liu*

Unsupervised Dense Prediction using Differentiable Normalized Cuts

"With the emergent attentive property of self-supervised Vision Transformer (ViT), Normalized Cuts (NCut) has resurfaced as a powerful tool for unsupervised dense prediction. However, the pre-trained ViT backbone (, DINO) is frozen in existing methods, which makes the feature extractor suboptimal fo…