Self-Supervised Learning of Object Parts for Semantic Segmentation. (arXiv:2204.13101v1 [cs.CV])

Progress in self-supervised learning has brought strong general image
representation learning methods. Yet so far, it has mostly focused on
image-level learning. In turn, tasks such as unsupervised image segmentation
have not benefited from this trend as they require spatially-diverse
representations. However, learning dense representations is challenging, as in
the unsupervised context it is not clear how to guide the model to learn
representations that correspond to various potential object categories. In this
paper, we argue that self-supervised learning of …

arxiv cv learning segmentation self-supervised learning semantic supervised learning