Shape Consistent 2D Keypoint Estimation under Domain Shift

08/04/2020
by   Levi O. Vasconcelos, et al.
0

Recent unsupervised domain adaptation methods based on deep architectures have shown remarkable performance not only in traditional classification tasks but also in more complex problems involving structured predictions (e.g. semantic segmentation, depth estimation). Following this trend, in this paper we present a novel deep adaptation framework for estimating keypoints under domain shift, i.e. when the training (source) and the test (target) images significantly differ in terms of visual appearance. Our method seamlessly combines three different components: feature alignment, adversarial training and self-supervision. Specifically, our deep architecture leverages from domain-specific distribution alignment layers to perform target adaptation at the feature level. Furthermore, a novel loss is proposed which combines an adversarial term for ensuring aligned predictions in the output space and a geometric consistency term which guarantees coherent predictions between a target sample and its perturbed version. Our extensive experimental evaluation conducted on three publicly available benchmarks shows that our approach outperforms state-of-the-art domain adaptation methods in the 2D keypoint prediction task.

READ FULL TEXT

page 4

page 6

research
12/15/2017

Unsupervised Domain Adaptation for 3D Keypoint Prediction from a Single Depth Scan

In this paper, we introduce a novel unsupervised domain adaptation techn...
research
05/17/2021

PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Training

Unsupervised domain adaptation is a promising technique for semantic seg...
research
08/11/2020

Learning to Cluster under Domain Shift

While unsupervised domain adaptation methods based on deep architectures...
research
12/21/2020

Unsupervised Domain Adaptation with Temporal-Consistent Self-Training for 3D Hand-Object Joint Reconstruction

Deep learning-solutions for hand-object 3D pose and shape estimation are...
research
03/25/2021

Inferring Latent Domains for Unsupervised Deep Domain Adaptation

Unsupervised Domain Adaptation (UDA) refers to the problem of learning a...
research
07/04/2022

Domain Adaptive Nuclei Instance Segmentation and Classification via Category-aware Feature Alignment and Pseudo-labelling

Unsupervised domain adaptation (UDA) methods have been broadly utilized ...
research
04/22/2020

A Cycle GAN Approach for Heterogeneous Domain Adaptation in Land Use Classification

In the field of remote sensing and more specifically in Earth Observatio...

Please sign up or login with your details

Forgot password? Click here to reset