MAPS: A Noise-Robust Progressive Learning Approach for Source-Free Domain Adaptive Keypoint Detection

by   Yuhe Ding, et al.

Existing cross-domain keypoint detection methods always require accessing the source data during adaptation, which may violate the data privacy law and pose serious security concerns. Instead, this paper considers a realistic problem setting called source-free domain adaptive keypoint detection, where only the well-trained source model is provided to the target domain. For the challenging problem, we first construct a teacher-student learning baseline by stabilizing the predictions under data augmentation and network ensembles. Built on this, we further propose a unified approach, Mixup Augmentation and Progressive Selection (MAPS), to fully exploit the noisy pseudo labels of unlabeled target data during training. On the one hand, MAPS regularizes the model to favor simple linear behavior in-between the target samples via self-mixup augmentation, preventing the model from over-fitting to noisy predictions. On the other hand, MAPS employs the self-paced learning paradigm and progressively selects pseudo-labeled samples from `easy' to `hard' into the training process to reduce noise accumulation. Results on four keypoint detection datasets show that MAPS outperforms the baseline and achieves comparable or even better results in comparison to previous non-source-free counterparts.


page 1

page 3

page 6

page 7

page 8

page 9


Cross-Domain Object Detection via Adaptive Self-Training

We tackle the problem of domain adaptation in object detection, where th...

ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection

In this paper, we present a self-training method, named ST3D++, with a h...

Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection

Unsupervised Domain Adaptation (UDA) is an effective approach to tackle ...

Self-training via Metric Learning for Source-Free Domain Adaptation of Semantic Segmentation

Unsupervised source-free domain adaptation methods aim to train a model ...

Adapting the Mean Teacher for keypoint-based lung registration under geometric domain shifts

Recent deep learning-based methods for medical image registration achiev...

Learning Articulated Shape with Keypoint Pseudo-labels from Web Images

This paper shows that it is possible to learn models for monocular 3D re...

Domain Adaptive Hand Keypoint and Pixel Localization in the Wild

We aim to improve the performance of regressing hand keypoints and segme...

Please sign up or login with your details

Forgot password? Click here to reset