Timezone: »
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)
-
2020 Poster: Self-Supervised Visual Representation Learning from Hierarchical Grouping »
Wed. Dec 9th 05:00 -- 07:00 AM Room Poster Session 2 #739
More from the Same Authors
-
2022 : On Convexity and Linear Mode Connectivity in Neural Networks »
David Yunis · Kumar Kshitij Patel · Pedro Savarese · Gal Vardi · Jonathan Frankle · Matthew Walter · Karen Livescu · Michael Maire -
2023 Poster: Accelerated Training via Incrementally Growing Neural Networks using Variance Transfer and Learning Rate Adaptation »
Xin Yuan · Pedro Savarese · Michael Maire -
2022 Poster: Not All Bits have Equal Value: Heterogeneous Precisions via Trainable Noise »
Pedro Savarese · Xin Yuan · Yanjing Li · Michael Maire -
2021 Poster: Online Meta-Learning via Learning with Layer-Distributed Memory »
Sudarshan Babu · Pedro Savarese · Michael Maire -
2020 Poster: Winning the Lottery with Continuous Sparsification »
Pedro Savarese · Hugo Silva · Michael Maire