Unsupervised part representation by Flow Capsules

11/27/2020
by   Sara Sabour, et al.
2

Capsule networks are designed to parse an image into a hierarchy of objects, parts and relations. While promising, they remain limited by an inability to learn effective low level part descriptions. To address this issue we propose a novel self-supervised method for learning part descriptors of an image. During training, we exploit motion as a powerful perceptual cue for part definition, using an expressive decoder for part generation and layered image formation with occlusion. Experiments demonstrate robust part discovery in the presence of multiple objects, cluttered backgrounds, and significant occlusion. The resulting part descriptors, a.k.a. part capsules, are decoded into shape masks, filling in occluded pixels, along with relative depth on single images. We also report unsupervised object classification using our capsule parts in a stacked capsule autoencoder.

READ FULL TEXT

page 6

page 7

research
04/30/2021

DPR-CAE: Capsule Autoencoder with Dynamic Part Representation for Image Parsing

Parsing an image into a hierarchy of objects, parts, and relations is im...
research
03/21/2022

HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network

Capsule networks are designed to present the objects by a set of parts a...
research
03/20/2023

Graphics Capsule: Learning Hierarchical 3D Face Representations from 2D Images

The function of constructing the hierarchy of objects is important to th...
research
01/15/2022

SS-3DCapsNet: Self-supervised 3D Capsule Networks for Medical Segmentation on Less Labeled Data

Capsule network is a recent new deep network architecture that has been ...
research
06/17/2019

Stacked Capsule Autoencoders

An object can be seen as a geometrically organized set of interrelated p...
research
03/11/2021

Inference for Generative Capsule Models

Capsule networks (see e.g. Hinton et al., 2018) aim to encode knowledge ...
research
03/12/2019

Unsupervised Discovery of Parts, Structure, and Dynamics

Humans easily recognize object parts and their hierarchical structure by...

Please sign up or login with your details

Forgot password? Click here to reset