Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
194 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Masked Contrastive Graph Representation Learning for Age Estimation (2306.17798v1)

Published 16 Jun 2023 in cs.CV

Abstract: Age estimation of face images is a crucial task with various practical applications in areas such as video surveillance and Internet access control. While deep learning-based age estimation frameworks, e.g., convolutional neural network (CNN), multi-layer perceptrons (MLP), and transformers have shown remarkable performance, they have limitations when modelling complex or irregular objects in an image that contains a large amount of redundant information. To address this issue, this paper utilizes the robustness property of graph representation learning in dealing with image redundancy information and proposes a novel Masked Contrastive Graph Representation Learning (MCGRL) method for age estimation. Specifically, our approach first leverages CNN to extract semantic features of the image, which are then partitioned into patches that serve as nodes in the graph. Then, we use a masked graph convolutional network (GCN) to derive image-based node representations that capture rich structural information. Finally, we incorporate multiple losses to explore the complementary relationship between structural information and semantic features, which improves the feature representation capability of GCN. Experimental results on real-world face image datasets demonstrate the superiority of our proposed method over other state-of-the-art age estimation approaches.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (53)
  1. Zeyuan Allen-Zhu and Yuanzhi Li. 2019. What can resnet learn efficiently, going beyond kernels? Advances in Neural Information Processing Systems 32 (2019).
  2. Vivit: A video vision transformer. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 6836–6846.
  3. Human age estimation using ranking svm. In Biometric Recognition: 7th Chinese Conference, CCBR 2012, Guangzhou, China, December 4-5, 2012. Proceedings 7. Springer, 324–331.
  4. Bipartite graph embedding via mutual information maximization. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining. 635–643.
  5. Rank consistent ordinal regression for neural networks with application to age estimation. Pattern Recognition Letters 140 (2020), 325–331.
  6. Kuang-Yu Chang and Chu-Song Chen. 2015. A learning framework for age rank estimation based on face images with scattering transform. IEEE Transactions on Image Processing 24, 3 (2015), 785–798.
  7. Ordinal hyperplanes ranker with cost sensitivities for age estimation. In CVPR 2011. IEEE, 585–592.
  8. Cumulative attribute space for age and crowd density estimation. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2467–2474.
  9. Deep age estimation: From classification to ranking. IEEE Transactions on Multimedia 20, 8 (2017), 2209–2222.
  10. An ensemble CNN2ELM for age estimation. IEEE Transactions on Information Forensics and Security 13, 3 (2017), 758–772.
  11. Deep label distribution learning with label ambiguity. IEEE Transactions on Image Processing 26, 6 (2017), 2825–2838.
  12. Facial Age Estimation by Learning from Label Distributions. In Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence. AAAI Press, 451–456.
  13. Facial age estimation by learning from label distributions. IEEE transactions on pattern analysis and machine intelligence 35, 10 (2013), 2401–2412.
  14. Automatic age estimation based on facial aging patterns. IEEE Transactions on pattern analysis and machine intelligence 29, 12 (2007), 2234–2240.
  15. Demographic estimation from face images: Human vs. machine performance. IEEE transactions on pattern analysis and machine intelligence 37, 6 (2014), 1148–1161.
  16. A survey on vision transformer. IEEE transactions on pattern analysis and machine intelligence 45, 1 (2022), 87–110.
  17. Kaveh Hassani and Amir Hosein Khasahmadi. 2020. Contrastive multi-view representation learning on graphs. In International Conference on Machine Learning. PMLR, 4116–4126.
  18. Shakediel Hiba and Yosi Keller. 2021. Hierarchical attention-based age estimation and Bias estimation. arXiv preprint arXiv:2103.09882 (2021).
  19. Facial age estimation with age difference. IEEE Transactions on Image Processing 26, 7 (2016), 3087–3097.
  20. Condensenet: An efficient densenet using learned group convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2752–2761.
  21. Thomas N Kipf and Max Welling. [n. d.]. Semi-Supervised Classification with Graph Convolutional Networks. In International Conference on Learning Representations.
  22. Loic Landrieu and Martin Simonovsky. 2018. Large-scale point cloud semantic segmentation with superpoint graphs. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4558–4567.
  23. Gil Levi and Tal Hassner. 2015. Age and gender classification using convolutional neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 34–42.
  24. Bridgenet: A continuity-aware probabilistic network for age estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 1145–1154.
  25. Microsoft coco: Common objects in context. In Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13. Springer, 740–755.
  26. Similarity-aware and variational deep adversarial learning for robust facial age estimation. IEEE Transactions on Multimedia 22, 7 (2020), 1808–1822.
  27. Agenet: Deeply learned regressor and classifier for robust apparent age estimation. In Proceedings of the IEEE International Conference on Computer Vision Workshops. 16–24.
  28. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 10012–10022.
  29. A convnet for the 2020s. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 11976–11986.
  30. Contourlet appearance model for facial age estimation. In 2011 international joint conference on biometrics (IJCB). IEEE, 1–8.
  31. Towards robust vision transformer. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 12042–12051.
  32. Simple unsupervised graph representation learning. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36. 7797–7805.
  33. Ordinal regression with multiple output cnn for age estimation. In Proceedings of the IEEE conference on computer vision and pattern recognition. 4920–4928.
  34. Some like it hot-visual guidance for preference prediction. In Proceedings of the IEEE conference on computer vision and pattern recognition. 5553–5561.
  35. Deep expectation of real and apparent age from a single image without facial landmarks. International Journal of Computer Vision 126, 2-4 (2018), 144–157.
  36. Deep differentiable random forests for age estimation. IEEE transactions on pattern analysis and machine intelligence 43, 2 (2019), 404–419.
  37. Deep regression forests for age estimation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2304–2313.
  38. Fetal brain age estimation and anomaly detection using attention-based deep ensembles with uncertainty. NeuroImage 223 (2020), 117316.
  39. Moving window regression: a novel approach to ordinal regression. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 18760–18769.
  40. V Betcy Thanga Shoba and I Shatheesh Sam. 2022. Adaptive deep feature learning based Softmax regressive classification for aging facial recognition. Multimedia Tools and Applications (2022), 1–29.
  41. Compressed-domain ship detection on spaceborne optical image using deep neural network and extreme learning machine. IEEE transactions on geoscience and remote sensing 53, 3 (2014), 1174–1185.
  42. Deep graph infomax. ICLR (Poster) 2, 3 (2019), 4.
  43. Improving face-based age estimation with attention-based dynamic patch fusion. IEEE Transactions on Image Processing 31 (2022), 1084–1096.
  44. Deeply-learned feature for age estimation. In 2015 IEEE Winter Conference on Applications of Computer Vision. IEEE, 534–541.
  45. Hybrid CNN and dictionary-based models for scene recognition and domain adaptation. IEEE Transactions on Circuits and Systems for Video Technology 27, 6 (2015), 1263–1274.
  46. Spatial temporal graph convolutional networks for skeleton-based action recognition. In Proceedings of the AAAI conference on artificial intelligence, Vol. 32.
  47. Dynamic graph cnn for learning on point clouds. ACM Transactions on Graphics (TOG) 38, 5 (2019).
  48. Jiaqi Zeng and Pengtao Xie. 2021. Contrastive self-supervised learning for graph classification. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 10824–10832.
  49. C3AE: Exploring the limits of compact model for age estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 12587–12596.
  50. Fine-grained age estimation in the wild with attention LSTM networks. IEEE Transactions on Circuits and Systems for Video Technology 30, 9 (2019), 3140–3152.
  51. Quantifying facial age by posterior of age comparisons. arXiv preprint arXiv:1708.09687 (2017).
  52. Yu Zhang and Dit-Yan Yeung. 2010. Multi-task warped gaussian process for personalized age estimation. In 2010 IEEE computer society conference on computer vision and pattern recognition. IEEE, 2622–2629.
  53. Graph contrastive learning with adaptive augmentation. In Proceedings of the Web Conference 2021. 2069–2080.
Citations (35)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now