mlsanityData to 7 Oct 2026

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

arXiv 2108.04893 ↗First posted 10 Aug 2021cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

The cost of head pose labeling is the main challenge of improving the fine-grained Head Pose Estimation (HPE). Although Self-Supervised Learning (SSL) can be a solution to the lack of huge amounts of labeled data, its efficacy for fine-grained HPE is not yet fully explored. This study aims to assess the usage of SSL in fine-grained HPE based on two scenarios: (1) using SSL for weights pre-training procedure, and (2) leveraging auxiliary SSL losses besides HPE. We design a Hybrid Multi-Task Learning (HMTL) architecture based on the ResNet50 backbone in which both strategies are applied. Our experimental results reveal that the combination of both scenarios is the best for HPE. Together, the average error rate is reduced up to 23.1% for AFLW2000 and 14.2% for BIWI benchmark compared to the baseline. Moreover, it is found that some SSL methods are more suitable for transfer learning, while others may be effective when they are considered as auxiliary tasks incorporated into supervised learning. Finally, it is shown that by using the proposed HMTL architecture, the average error is reduced with different types of initial weights: random, ImageNet and SSL pre-trained weights.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 36 of its 56 references that are in the map. First posted on arXiv 10 Aug 2021.

Builds on

36 of 56 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  4. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  5. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  6. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
  7. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  8. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  9. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  10. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  11. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  12. 2016Colorful Image Colorizationcited by 1,113
24 more
  1. 2020Multi-Task Learning with Deep Neural Networks: A Surveycited by 374
  2. 2019Which Tasks Should Be Learned Together in Multi-task Learning?cited by 367
  3. 2019S4L: Self-Supervised Semi-Supervised Learningcited by 335
  4. 2020AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradientscited by 282
  5. 2018Cooperative Learning of Audio and Video Models from Self-Supervised Synchronizationcited by 246
  6. 2020Self-supervised Co-training for Video Representation Learningcited by 232
  7. 2017Fine-Grained Head Pose Estimation Without Keypointscited by 163
  8. 2020ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variationcited by 141
  9. 2019Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labelscited by 111
  10. 2021When Does Contrastive Visual Representation Learning Work?cited by 92
  11. 2019A critical analysis of self-supervision, or what we can learn from a single imagecited by 75
  12. 2020img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimationcited by 57
  13. 2017Towards Large-Pose Face Frontalization in the Wildcited by 50
  14. 2020WHENet: Real-time Fine-Grained Estimation for Wide Range Head Posecited by 47
  15. 2019MultiNet++: Multi-Stream Feature Aggregation and Geometric Loss Strategy for Multi-Task Learningcited by 45
  16. 2020Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesiscited by 44
  17. 2020A Vector-based Representation to Enhance Head Pose Estimationcited by 34
  18. 2018Pose-Robust Face Recognition via Deep Residual Equivariant Mappingcited by 28
  19. 2020Self-Supervised Viewpoint Learning From Image Collectionscited by 23
  20. 2019Facial Pose Estimation by Deep Learning from Label Distributionscited by 10
  21. 2021Using Self-Supervised Auxiliary Tasks to Improve Fine-Grained Facial Representationcited by 7
  22. 2019A Realistic Face-to-Face Conversation System based on Deep Neural Networkscited by 6
  23. 2019Video synthesis of human upper body with realistic facecited by 4
  24. 2019Hybrid coarse-fine classification for head pose estimationcited by 2

Built on by

Not cited yet.