2000 character limit reached
A Call to Reflect on Evaluation Practices for Age Estimation: Comparative Analysis of the State-of-the-Art and a Unified Benchmark
Published 10 Jul 2023 in cs.CV and cs.LG | (2307.04570v3)
Abstract: Comparing different age estimation methods poses a challenge due to the unreliability of published results stemming from inconsistencies in the benchmarking process. Previous studies have reported continuous performance improvements over the past decade using specialized methods; however, our findings challenge these claims. This paper identifies two trivial, yet persistent issues with the currently used evaluation protocol and describes how to resolve them. We offer an extensive comparative analysis for state-of-the-art facial age estimation methods. Surprisingly, we find that the performance differences between the methods are negligible compared to the effect of other factors, such as facial alignment, facial coverage, image resolution, model architecture, or the amount of data used for pretraining. We use the gained insights to propose using FaRL as the backbone model and demonstrate its effectiveness on all public datasets. We make the source code and exact data splits public on GitHub.
- Apparent and real age estimation in still images with deep residual regressors on appa-real database. In 12th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), 2017. IEEE, 2017.
- Deep ordinal regression with label diversity. In 2020 25th International Conference on Pattern Recognition (ICPR), pages 2740–2747, Los Alamitos, CA, USA, 2021. IEEE Computer Society.
- Rank consistent ordinal regression for neural networks with application to age estimation. Pattern Recognition Letters, 140:325–331, 2020.
- Cross-age reference coding for age-invariant face recognition and retrieval. In Computer Vision – ECCV 2014, pages 768–783, Cham, 2014. Springer International Publishing.
- Using ranking-cnn for age estimation. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 742–751, 2017.
- Janez Demšar. Statistical comparisons of classifiers over multiple data sets. The Journal of Machine learning research, 7:1–30, 2006.
- Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 248–255, 2009.
- Retinaface: Single-shot multi-level face localisation in the wild. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5203–5212, 2020.
- An image is worth 16x16 words: Transformers for image recognition at scale. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net, 2021.
- Soft labels for ordinal regression. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 4733–4742, 2019.
- Chalearn looking at people 2015: Apparent age and cultural event recognition datasets and results. In 2015 IEEE International Conference on Computer Vision Workshop (ICCVW), pages 243–251, 2015.
- Learning cnns from weakly annotated facial images. Image and Vision Computing, 2018.
- Deep label distribution learning with label ambiguity. IEEE Transactions on Image Processing, 26(6):2825–2838, 2017.
- Age estimation using expectation of label distribution learning. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18, pages 712–718. International Joint Conferences on Artificial Intelligence Organization, 2018.
- Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 770–778, 2016.
- Toward automatic simulation of aging effects on face images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(4):442–455, 2002.
- Ordinal regression by extended binary classification. In Advances in Neural Information Processing Systems, page 865 – 872, 2007. Cited by: 195.
- Unimodal-concentrated loss: Fully adaptive label distribution learning for ordinal regression. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 20513–20522, 2022.
- Roi tanh-polar transformer network for face parsing in the wild. Image and Vision Computing, 112, 2021.
- Fp-age: Leveraging face parsing attention for facial age estimation in the wild. IEEE Transactions on Image Processing, 2022.
- Agedb: the first manually collected, in-the-wild age database. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshop, 2017.
- Ordinal regression with multiple output cnn for age estimation. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 4920–4928, 2016.
- Mean-variance loss for deep age estimation from a face. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5285–5294, 2018.
- Morph: a longitudinal image database of normal adult age-progression. In 7th International Conference on Automatic Face and Gesture Recognition (FGR06), pages 341–345, 2006.
- Dex: Deep expectation of apparent age from a single image. In 2015 IEEE International Conference on Computer Vision Workshop (ICCVW), pages 252–257, 2015.
- Deep expectation of real and apparent age from a single image without facial landmarks. International Journal of Computer Vision, 126(2-4):144–157, 2018.
- LAION-5b: An open large-scale dataset for training next generation image-text models. In Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 2022.
- Moving window regression: A novel approach to ordinal regression. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 18760–18769, 2022.
- Quantifying facial age by posterior of age comparisons. In Proceedings of the British Machine Vision Conference (BMVC), pages 108.1–108.12. BMVA Press, 2017a.
- Age progression/regression by conditional adversarial autoencoder. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2017b.
- General facial representation learning in a visual-linguistic manner. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 18697–18709, 2022.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.