Corpus ID: 198186558

Unsupervised Domain Adaptation via Calibrating Uncertainties

  title={Unsupervised Domain Adaptation via Calibrating Uncertainties},
  author={Ligong Han and Yang Zou and Ruijiang Gao and L. Wang and Dimitris N. Metaxas},
Unsupervised domain adaptation (UDA) aims at inferring class labels for unlabeled target domain given a related labeled source dataset. Intuitively, a model trained on source domain normally produces higher uncertainties for unseen data. In this work, we build on this assumption and propose to adapt from source to target domain via calibrating their predictive uncertainties. The uncertainty is quantified as the Renyi entropy, from which we propose a general Renyi entropy regularization (RER… Expand
7 Citations
Unsupervised Domain Adaptation by Uncertain Feature Alignment
  • PDF
Energy-constrained Self-training for Unsupervised Domain Adaptation
  • 1
  • PDF
Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation
  • 28
  • PDF
Confidence Regularized Self-Training
  • 138
  • PDF
Generalizing Hand Segmentation in Egocentric Videos With Uncertainty-Guided Model Adaptation
  • Minjie Cai, Feng Lu, Y. Sato
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
  • 3
  • PDF
Conservative Wasserstein Training for Pose Estimation
  • 21
  • PDF
Addressing Failure Prediction by Learning Model Confidence
  • 43
  • PDF


Co-regularized Alignment for Unsupervised Domain Adaptation
  • 64
  • PDF
Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-training
  • 322
  • PDF
A DIRT-T Approach to Unsupervised Domain Adaptation
  • 268
  • PDF
Semi-supervised Learning by Entropy Minimization
  • 924
  • PDF
beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework
  • 1,776
ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
  • 214
  • PDF
Deep Transfer Network: Unsupervised Domain Adaptation
  • 84
  • PDF
Generate to Adapt: Aligning Domains Using Generative Adversarial Networks
  • 325
  • PDF
Regularizing Neural Networks by Penalizing Confident Output Distributions
  • 524
  • PDF
Adversarial Discriminative Domain Adaptation
  • 1,957
  • PDF