mlsanityData to 7 Oct 2026

Jitter Does Matter: Adapting Gaze Estimation to New Domains

arXiv 2210.02082 ↗First posted 5 Oct 2022cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Deep neural networks have demonstrated superior performance on appearance-based gaze estimation tasks. However, due to variations in person, illuminations, and background, performance degrades dramatically when applying the model to a new domain. In this paper, we discover an interesting gaze jitter phenomenon in cross-domain gaze estimation, i.e., the gaze predictions of two similar images can be severely deviated in target domain. This is closely related to cross-domain gaze estimation tasks, but surprisingly, it has not been noticed yet previously. Therefore, we innovatively propose to utilize the gaze jitter to analyze and optimize the gaze domain adaptation task. We find that the high-frequency component (HFC) is an important factor that leads to jitter. Based on this discovery, we add high-frequency components to input images using the adversarial attack and employ contrastive learning to encourage the model to obtain similar representations between original and perturbed data, which reduces the impacts of HFC. We evaluate the proposed method on four cross-domain gaze estimation tasks, and experimental results demonstrate that it significantly reduces the gaze jitter and improves the gaze estimation performance in target domains.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 34 of its 50 references that are in the map. First posted on arXiv 5 Oct 2022.

Builds on

34 of 50 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2013Intriguing properties of neural networkscited by 5,114
  7. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  8. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  9. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  10. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  11. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  12. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 636
22 more
  1. 2018Deep Visual Domain Adaptation: A Surveycited by 634
  2. 2017One pixel attack for fooling deep neural networkscited by 579
  3. 2016Domain Separation Networkscited by 317
  4. 2019High Frequency Component Helps Explain the Generalization of Convolutional Neural Networkscited by 310
  5. 2016Learning from Simulated and Unsupervised Images through Adversarial Trainingcited by 287
  6. 2019Gaze360: Physically Unconstrained Gaze Estimation in the Wildcited by 173
  7. 2019Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systemscited by 151
  8. 2020ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variationcited by 141
  9. 2020Gradually Vanishing Bridge for Adversarial Domain Adaptationcited by 130
  10. 2021Deep Subdomain Adaptation Network for Image Classificationcited by 119
  11. 2017MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimationcited by 118
  12. 2019Few-Shot Adaptive Gaze Estimationcited by 77
  13. 2020A Coarse-to-Fine Adaptive Network for Appearance-Based Gaze Estimationcited by 66
  14. 2019Training Robust Deep Neural Networks via Adversarial Noise Propagationcited by 60
  15. 2021PureGaze: Purifying Gaze Feature for Generalizable Gaze Estimationcited by 54
  16. 2014Domain Adaptive Neural Networks for Object Recognitioncited by 51
  17. 2019Improving Few-Shot User-Specific Gaze Adaptation via Gaze Redirection Synthesiscited by 43
  18. 2021Generalizing Gaze Estimation with Outlier-guided Collaborative Adaptationcited by 42
  19. 2019Transfer Learning with Dynamic Adversarial Adaptation Networkcited by 37
  20. 2021Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learningcited by 30
  21. 2020Domain Adaptation Gaze Estimation by Embedding with Prediction Consistencycited by 27
  22. 2021Exploring Robustness of Unsupervised Domain Adaptation in Semantic Segmentationcited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 2; 2025: 1; 2026: 1.

6 papers.

  1. 2024Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimationcited by 19
  2. 2024LG-Gaze: Learning Geometry-aware Continuous Prompts for Language-Guided Gaze Estimationcited by 9
  3. 2025UniGaze: Towards Universal Gaze Estimation via Large-scale Pre-Trainingcited by 8
  4. 2023Domain-Adaptive Full-Face Gaze Estimation via Novel-View-Synthesis and Feature Disentanglementcited by 3
  5. 2022Contrastive Weighted Learning for Near-Infrared Gaze Estimationcited by 0
  6. 2026GMGaze: MoE-Based Context-Aware Gaze Estimation with CLIP and Multiscale Transformercited by 0