Semi-Supervised 2D Human Pose Estimation Driven by Position Inconsistency Pseudo Label Correction Module
In this paper, we delve into semi-supervised 2D human pose estimation. The previous method ignored two problems: (i) When conducting interactive training between large model and lightweight model, the pseudo label of lightweight model will be used to guide large models. (ii) The negative impact of noise pseudo labels on training. Moreover, the labels used for 2D human pose estimation are relatively complex: keypoint category and keypoint position. To solve the problems mentioned above, we propose a semi-supervised 2D human pose estimation framework driven by a position inconsistency pseudo label correction module (SSPCM). We introduce an additional auxiliary teacher and use the pseudo labels generated by the two teacher model in different periods to calculate the inconsistency score and remove outliers. Then, the two teacher models are updated through interactive training, and the student model is updated using the pseudo labels generated by two teachers. To further improve the performance of the student model, we use the semi-supervised Cut-Occlude based on pseudo keypoint perception to generate more hard and effective samples. In addition, we also proposed a new indoor overhead fisheye human keypoint dataset WEPDTOF-Pose. Extensive experiments demonstrate that our method outperforms the previous best semi-supervised 2D human pose estimation method. We will release the code and dataset at https://github.com/hlz0606/SSPCM.
Code (1)
Tasks
2D Human Pose EstimationPose EstimationPositionPseudo LabelSimilar Papers 제목 키워드 기반
Semi-Supervised Model-Free Bayesian State Estimation from Compressed Measurements
We consider data-driven Bayesian state estimation from compressed measurements (BSCM) of a model-free process. The dimension of the temporal measurement vector is lower than that of the temporal state vector to be estima…
State EstimationSemi- and Weakly-supervised Human Pose Estimation
For human pose estimation in still images, this paper proposes three semi- and weakly-supervised learning schemes. While recent advances of convolutional neural networks improve human pose estimation using supervised tra…
ClusteringPose EstimationWeakly-supervised LearningSemi-supervised 2D Human Pose Estimation via Adaptive Keypoint Masking
Human pose estimation is a fundamental and challenging task in computer vision. Larger-scale and more accurate keypoint annotations, while helpful for improving the accuracy of supervised pose estimation, are often expen…
2D Human Pose EstimationData AugmentationPose EstimationAutomatic Pronunciation Generation by Utilizing a Semi-supervised Deep Neural Networks
Phonemic or phonetic sub-word units are the most commonly used atomic elements to represent speech signals in modern ASRs. However they are not the optimal choice due to several reasons such as: large amount of effort re…
speech-recognitionSpeech RecognitionA New Teacher-Reviewer-Student Framework for Semi-supervised 2D Human Pose Estimation
Conventional 2D human pose estimation methods typically require extensive labeled annotations, which are both labor-intensive and expensive. In contrast, semi-supervised 2D human pose estimation can alleviate the above p…
2D Human Pose EstimationData AugmentationPose Estimation