Skip to yearly menu bar Skip to main content


Poster
in
Workshop: 4th Workshop on Self-Supervised Learning: Theory and Practice

Understanding Self-Supervised Features for Learning Unsupervised Instance Segmentation

Paul Engstler · Luke Melas-Kyriazi · Christian Rupprecht · Iro Laina


Abstract:

Self-supervised learning (SSL) can be used to solve complex visual tasks without human labels. Self-supervised representations encode useful semantic information about images, and as a result, they have already been used for tasks such as unsupervised semantic segmentation.In this paper, we investigate self-supervised representations for instance segmentation without any manual annotations.We find that the features of different SSL methods vary in their level of instance-awareness. In particular, DINO features, which are known to be excellent semantic descriptors, lack behind MAE features in their sensitivity for separating instances.

Chat is not available.