Self-Supervised Visual Representation Learning from Hierarchical Grouping

12/05/2020
by   Xiao Zhang, et al.
0

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.

READ FULL TEXT

page 2

page 7

page 8

page 9

research
01/18/2022

RePre: Improving Self-Supervised Vision Transformer with Reconstructive Pre-training

Recently, self-supervised vision transformers have attracted unprecedent...
research
05/30/2022

Self-Supervised Visual Representation Learning with Semantic Grouping

In this paper, we tackle the problem of learning visual representations ...
research
11/23/2021

ReGroup: Recursive Neural Networks for Hierarchical Grouping of Vector Graphic Primitives

Selection functionality is as fundamental to vector graphics as it is fo...
research
09/30/2021

Motion-aware Self-supervised Video Representation Learning via Foreground-background Merging

In light of the success of contrastive learning in the image domain, cur...
research
06/13/2021

InfoBehavior: Self-supervised Representation Learning for Ultra-long Behavior Sequence via Hierarchical Grouping

E-commerce companies have to face abnormal sellers who sell potentially-...
research
04/03/2023

Associating Spatially-Consistent Grouping with Text-supervised Semantic Segmentation

In this work, we investigate performing semantic segmentation solely thr...
research
03/25/2020

Deep Grouping Model for Unified Perceptual Parsing

The perceptual-based grouping process produces a hierarchical and compos...

Please sign up or login with your details

Forgot password? Click here to reset