Details

Autor(en) / Beteiligte

• Yoo, Nobline
• Russakovsky, Olga

Titel

Efficient, Self-Supervised Human Pose Estimation with Inductive Prior Tuning

Ist Teil von

• 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2023, p.3263-3272

Ort / Verlag

IEEE

Erscheinungsjahr

2023

Quelle

IEEE Xplore

Beschreibungen/Notizen

• The goal of 2D human pose estimation (HPE) is to localize anatomical landmarks, given an image of a person in a pose. SOTA techniques make use of thousands of labeled figures (finetuning transformers or training deep CNNs), acquired using labor-intensive crowdsourcing. On the other hand, self-supervised methods re-frame the HPE task as a reconstruction problem, enabling them to leverage the vast amount of unlabeled visual data, though at the present cost of accuracy. In this work, we explore ways to improve self-supervised HPE. We (1) analyze the relationship between reconstruction quality and pose estimation accuracy, (2) develop a model pipeline that outperforms the baseline which inspired our work, using less than one-third the amount of training data, and (3) offer a new metric suitable for self-supervised settings that measures the consistency of predicted body part length proportions. We show that a combination of well-engineered reconstruction losses and inductive priors can help coordinate pose learning alongside reconstruction in a self-supervised paradigm.