Contrastive Representation Learning for Hand Shape Estimation

06/08/2021
by   Christian Zimmermann, et al.
0

This work presents improvements in monocular hand shape estimation by building on top of recent advances in unsupervised learning. We extend momentum contrastive learning and contribute a structured collection of hand images, well suited for visual representation learning, which we call HanCo. We find that the representation learned by established contrastive learning methods can be improved significantly by exploiting advanced background removal techniques and multi-view information. These allow us to generate more diverse instance pairs than those obtained by augmentations commonly used in exemplar based approaches. Our method leads to a more suitable representation for the hand shape estimation task and shows a 4.7 improvement in F-score compared to an ImageNet pretrained baseline. We make our benchmark dataset publicly available, to encourage further research into this direction.

READ FULL TEXT

page 1

page 2

page 3

page 5

page 6

research
07/13/2022

Unsupervised Visual Representation Learning by Synchronous Momentum Grouping

In this paper, we propose a genuine group-level contrastive visual repre...
research
11/26/2020

Beyond Single Instance Multi-view Unsupervised Representation Learning

Recent unsupervised contrastive representation learning follows a Single...
research
01/19/2022

TriCoLo: Trimodal Contrastive Loss for Fine-grained Text to Shape Retrieval

Recent work on contrastive losses for learning joint embeddings over mul...
research
11/13/2019

Momentum Contrast for Unsupervised Visual Representation Learning

We present Momentum Contrast (MoCo) for unsupervised visual representati...
research
05/18/2021

Multi-view Contrastive Coding of Remote Sensing Images at Pixel-level

Our planet is viewed by satellites through multiple sensors (e.g., multi...
research
04/01/2021

Jigsaw Clustering for Unsupervised Visual Representation Learning

Unsupervised representation learning with contrastive learning achieved ...

Please sign up or login with your details

Forgot password? Click here to reset