Regressive Domain Adaptation for Unsupervised Keypoint Detection

@article{Jiang2021RegressiveDA,
  title={Regressive Domain Adaptation for Unsupervised Keypoint Detection},
  author={Junguang Jiang and Yifei Ji and Ximei Wang and Yufeng Liu and Jianmin Wang and Mingsheng Long},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2021},
  pages={6776-6785}
}
Domain adaptation (DA) aims at transferring knowledge from a labeled source domain to an unlabeled target domain. Though many DA theories and algorithms have been proposed, most of them are tailored into classification settings and may fail in regression tasks, especially in the practical keypoint detection task. To tackle this difficult but significant task, we present a method of regressive domain adaptation (RegDA) for unsupervised keypoint detection. Inspired by the latest theoretical work… Expand
Learning Transferable Parameters for Unsupervised Domain Adaptation
  • Zhongyi Han, Haoliang Sun, Yilong Yin
  • Computer Science
  • ArXiv
  • 2021
TLDR
This paper finds that only partial parameters are essential for learning domain-invariant information and generalizing well in UDA, and proposes Transferable Parameter Learning (TransPar), which can be integrated into the most popular deep UDA networks and be easily extended to handle any data distribution shift scenarios. Expand
Action Recognition with Domain Invariant Features of Skeleton Image
  • Han Chen, Yifan Jiang, Hanseok Ko
  • Computer Science, Engineering
  • ArXiv
  • 2021
TLDR
A novel CNN-based method with adversarial training for action recognition that achieves competitive results compared with state-of-the-art methods and 2.4%, 1.9% accuracy gain than the baseline for cross-subject and crossview. Expand
Decoupled Adaptation for Cross-Domain Object Detection
  • Junguang Jiang, Baixu Chen, Jianmin Wang, Mingsheng Long
  • Computer Science
  • ArXiv
  • 2021
TLDR
D-adapt is proposed, namely Decoupled Adaptation, to decouple the adversarial adaptation and the training of the detector and fills the blank of regression domain adaptation in object detection by introducing a bounding box adaptor. Expand
Towards Accurate Cross-Domain In-Bed Human Pose Estimation
TLDR
A novel learning strategy comprises of two-fold data augmentation to reduce the cross-domain discrepancy and knowledge distillation to learn the distribution of unlabeled images in real world conditions. Expand

References

SHOWING 1-10 OF 41 REFERENCES
Domain-Adversarial Training of Neural Networks
TLDR
A new representation learning approach for domain adaptation, in which data at training and test time come from similar but different distributions, which can be achieved in almost any feed-forward model by augmenting it with few standard layers and a new gradient reversal layer. Expand
Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
TLDR
A new approach that attempts to align distributions of source and target by utilizing the task-specific decision boundaries by maximizing the discrepancy between two classifiers' outputs to detect target samples that are far from the support of the source. Expand
Bridging Theory and Algorithm for Domain Adaptation
TLDR
Margin Disparity Discrepancy is introduced, a novel measurement with rigorous generalization bounds, tailored to the distribution comparison with the asymmetric margin loss, and to the minimax optimization for easier training. Expand
Learning Transferable Features with Deep Adaptation Networks
TLDR
A new Deep Adaptation Network (DAN) architecture is proposed, which generalizes deep convolutional neural network to the domain adaptation scenario and can learn transferable features with statistical guarantees, and can scale linearly by unbiased estimate of kernel embedding. Expand
A theory of learning from different domains
TLDR
A classifier-induced divergence measure that can be estimated from finite, unlabeled samples from the domains and shows how to choose the optimal combination of source and target error as a function of the divergence, the sample sizes of both domains, and the complexity of the hypothesis class. Expand
Adversarial PoseNet: A Structure-Aware Convolutional Network for Human Pose Estimation
TLDR
This work proposes a novel structure-aware convolutional network to implicitly take priors about the structure of human bodies into account during training of the deep network and significantly outperforms the state-of-the-art methods and almost always generates plausible human pose predictions. Expand
Adapting Visual Category Models to New Domains
TLDR
This paper introduces a method that adapts object models acquired in a particular visual domain to new imaging conditions by learning a transformation that minimizes the effect of domain-induced changes in the feature distribution. Expand
Unsupervised Domain Adaptation for 3D Keypoint Estimation via View Consistency
TLDR
A novel unsupervised domain adaptation technique for the task of 3D keypoint prediction from a single depth scan or image using the fact that predictions from different views of the same or similar objects should be consistent with each other is introduced. Expand
Convolutional Pose Machines
TLDR
This work designs a sequential architecture composed of convolutional networks that directly operate on belief maps from previous stages, producing increasingly refined estimates for part locations, without the need for explicit graphical model-style inference in structured prediction tasks such as articulated pose estimation. Expand
Virtual and Real World Adaptation for Pedestrian Detection
TLDR
A domain adaptation framework, V-AYLA, in which different techniques to collect a few pedestrian samples from the target domain and combine them with the many examples of the source domain in order to train a domain adapted pedestrian classifier that will operate in thetarget domain. Expand
...
1
2
3
4
5
...