DeepAI AI Chat
Log In Sign Up

Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentation

by   Takehiko Ohkawa, et al.
The University of Tokyo

Hand segmentation is a crucial task in first-person vision. Since first-person images exhibit strong bias in appearance among different environments, adapting a pre-trained segmentation model to a new domain is required in hand segmentation. Here, we focus on appearance gaps for hand regions and backgrounds separately. We propose (i) foreground-aware image stylization and (ii) consensus pseudo-labeling for domain adaptation of hand segmentation. We stylize source images independently for the foreground and background using target images as style. To resolve the domain shift that the stylization has not addressed, we apply careful pseudo-labeling by taking a consensus between the models trained on the source and stylized source images. We validated our method on domain adaptation of hand segmentation from real and simulation images. Our method achieved state-of-the-art performance in both settings. We also demonstrated promising results in challenging multi-target domain adaptation and domain generalization settings. Code is available at


page 1

page 3

page 4

page 5

page 8

page 9

page 10

page 11


1st Place Solution to NeurIPS 2022 Challenge on Visual Domain Adaptation

The Visual Domain Adaptation(VisDA) 2022 Challenge calls for an unsuperv...

Carton dataset synthesis based on foreground texture replacement

One major impediment in rapidly deploying object detection models for in...

EANet: Enhancing Alignment for Cross-Domain Person Re-identification

Person re-identification (ReID) has achieved significant improvement und...

Left/Right Hand Segmentation in Egocentric Videos

Wearable cameras allow people to record their daily activities from a us...

3D Masked Autoencoding and Pseudo-labeling for Domain Adaptive Segmentation of Heterogeneous Infant Brain MRI

Robust segmentation of infant brain MRI across multiple ages, modalities...

A Fully Convolutional Tri-branch Network (FCTN) for Domain Adaptation

A domain adaptation method for urban scene segmentation is proposed in t...

Weakly-supervised Caricature Face Parsing through Domain Adaptation

A caricature is an artistic form of a person's picture in which certain ...

Code Repositories


Official implementation of "Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentation" (IEEE Access 2021)

view repo