Timezone: »

Self-Supervised Visual Representation Learning from Hierarchical Grouping
Xiao Zhang · Michael Maire

Tue Dec 08 07:00 PM -- 07:10 PM (PST) @ Orals & Spotlights: Vision Applications

We create a framework for bootstrapping visual representation learning from a primitive visual grouping capability. We operationalize grouping via a contour detector that partitions an image into regions, followed by merging of those regions into a tree hierarchy. A small supervised dataset suffices for training this grouping primitive. Across a large unlabeled dataset, we apply this learned primitive to automatically predict hierarchical region structure. These predictions serve as guidance for self-supervised contrastive feature learning: we task a deep network with producing per-pixel embeddings whose pairwise distances respect the region hierarchy. Experiments demonstrate that our approach can serve as state-of-the-art generic pre-training, benefiting downstream tasks. We additionally explore applications to semantic region search and video-based object instance tracking.

Author Information

Xiao Zhang (University of Chicago)
Michael Maire (University of Chicago)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors