Invariant Teacher and Equivariant Student for Unsupervised 3D Human Pose Estimation

2020-12-17 · Chenxin Xu, Siheng Chen, Maosen Li, Ya zhang

We propose a novel method based on teacher-student learning framework for 3D human pose estimation without any 3D annotation or side information. To solve this unsupervised-learning problem, the teacher network adopts pose-dictionary-based modeling for regularization to estimate a physically plausible 3D pose. To handle the decomposition ambiguity in the teacher network, we propose a cycle-consistent architecture promoting a 3D rotation-invariant property to train the teacher network. To further improve the estimation accuracy, the student network adopts a novel graph convolution network for flexibility to directly estimate the 3D coordinates. Another cycle-consistent architecture promoting 3D rotation-equivariant property is adopted to exploit geometry consistency, together with knowledge distillation from the teacher network to improve the pose estimation performance. We conduct extensive experiments on Human3.6M and MPI-INF-3DHP. Our method reduces the 3D joint prediction error by 11.4% compared to state-of-the-art unsupervised methods and also outperforms many weakly-supervised methods that use side information on Human3.6M. Code will be available at https://github.com/sjtuxcx/ITES.

📄 PDF Abstract BibTeX arXiv:2012.09398

Code (1)

sjtuxcx/ITES 공식 구현 pytorch

Tasks

3D Human Pose Estimation Knowledge Distillation Pose Estimation Unsupervised 3D Human Pose Estimation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Teacher-Student Competition for Unsupervised Domain Adaptation

2020-10-19 · Ruixin Xiao, Zhilei Liu, Baoyuan Wu

With the supervision from source domain only in class-level, existing unsupervised domain adaptation (UDA) methods mainly learn the domain-invariant representations from a shared feature extractor, which causes the sourc…

Domain Adaptation Unsupervised Domain Adaptation

Teacher-Student MixIT for Unsupervised and Semi-supervised Speech Separation

2021-06-15 · Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker

In this paper, we introduce a novel semi-supervised learning framework for end-to-end speech separation. The proposed method first uses mixtures of unseparated sources and the mixture invariant training (MixIT) criterion…

Speech Separation

Unsupervised Representation Transfer for Small Networks: I Believe I Can Distill On-the-Fly

2021-12-01 · NeurIPS 2021 12 · Hee Min Choi, Hyoa Kang, Dokwan Oh

A current remarkable improvement of unsupervised visual representation learning is based on heavy networks with large-batch training. While recent methods have greatly reduced the gap between supervised and unsupervised …

Knowledge Distillation Linear evaluation Representation Learning Transfer Learning

Remixing-based Unsupervised Source Separation from Scratch

2023-09-01 · Kohei Saijo, Tetsuji Ogawa

We propose an unsupervised approach for training separation models from scratch using RemixIT and Self-Remixing, which are recently proposed self-supervised learning methods for refining pre-trained models. They first se…

Self-Supervised Learning

Adversarial Teacher-Student Learning for Unsupervised Domain Adaptation

2018-04-02 · Zhong Meng, Jinyu Li, Yifan Gong, Biing-Hwang 외

The teacher-student (T/S) learning has been shown effective in unsupervised domain adaptation [1]. It is a form of transfer learning, not in terms of the transfer of recognition decisions, but the knowledge of posteriori…

Domain Adaptation Transfer Learning Unsupervised Domain Adaptation