Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Bias release_rvs5uox2fbg6ppwyxi2yrpwbfi

by Stefan Stojanov, Anh Thai, James M. Rehg

Released as a article .

2021  

Abstract

It is widely accepted that reasoning about object shape is important for object recognition. However, the most powerful object recognition methods today do not explicitly make use of object shape during learning. In this work, motivated by recent developments in low-shot learning, findings in developmental psychology, and the increased use of synthetic data in computer vision research, we investigate how reasoning about 3D shape can be used to improve low-shot learning methods' generalization performance. We propose a new way to improve existing low-shot learning approaches by learning a discriminative embedding space using 3D object shape, and utilizing this embedding by learning how to map images into it. Our new approach improves the performance of image-only low-shot learning approaches on multiple datasets. We also develop Toys4K, a new 3D object dataset with the biggest number of object categories that can also support low-shot learning.
In text/plain format

Archived Files and Locations

application/pdf  8.5 MB
file_oksj6rm735e6bcdzlrrlrfmb34
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2021-01-18
Version   v1
Language   en ?
arXiv  2101.07296v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: bca6dfe7-8a4a-4cc8-8fa0-70ad14143ac4
API URL: JSON