DeepAI AI Chat
Log In Sign Up

How Self-Supervised Learning Can be Used for Fine-Grained Head Pose Estimation?

by   Mahdi Pourmirzaei, et al.

Recent progress of Self-Supervised Learning (SSL) demonstrates the capability of these methods in computer vision field. However, this progress could not show any promises for fine-grained tasks such as Head Pose estimation. In this article, we have tried to answer a question: How SSL can be used for Head Pose estimation? In general, there are two main approaches to use SSL: (1) Using pre-trained weights which can be done via SSL tasks, (2) Leveraging SSL as an auxiliary co-training task besides of Supervised Learning (SL) tasks at the same time. In this study, modified versions of jigsaw puzzling and rotation as SSL pre-text tasks are used and the best architecture for our proposed Hybrid Multi-Task Learning (HMTL) is found. Finally, the HopeNet method as a baseline SL is selected and the impact of SSL pre-training and ImageNet pre-training on both HMTL and SL are compared. The error rate reduced by the HMTL method up to 13 kinds of initial weights: random, ImageNet and SSL pre-training weights. Also, it was observed, when puzzled images are used for SL alone, the average error rate placed between SL and HMTL, showed the importance of local spatial features compare to global spatial features.


Using Self-Supervised Co-Training to Improve Facial Representation

In this paper, at first, the impact of ImageNet pre-training on Facial E...

Rethinking Self-Supervised Visual Representation Learning in Pre-training for 3D Human Pose and Shape Estimation

Recently, a few self-supervised representation learning (SSL) methods ha...

Learning to Estimate External Forces of Human Motion in Video

Analyzing sports performance or preventing injuries requires capturing g...

PRSNet: A Masked Self-Supervised Learning Pedestrian Re-Identification Method

In recent years, self-supervised learning has attracted widespread acade...

Part-Aware Self-Supervised Pre-Training for Person Re-Identification

In person re-identification (ReID), very recent researches have validate...

What makes ImageNet good for transfer learning?

The tremendous success of ImageNet-trained deep features on a wide range...

LwPosr: Lightweight Efficient Fine-Grained Head Pose Estimation

This paper presents a lightweight network for head pose estimation (HPE)...