LAE : Long-tailed Age Estimation

• URL: http://arxiv.org/abs/2110.12741v1
• Date: Mon, 25 Oct 2021 09:05:44 GMT
• Title: LAE : Long-tailed Age Estimation
• Authors: Zenghao Bao, Zichang Tan, Yu Zhu, Jun Wan, Xibo Ma, Zhen Lei, Guodong Guo
• Abstract summary: We first formulate a simple standard baseline and build a much strong one by collecting the tricks in pre-training, data augmentation, model architecture, and so on. Compared with the standard baseline, the proposed one significantly decreases the estimation errors. We propose a two-stage training method named Long-tailed Age Estimation (LAE), which decouples the learning procedure into representation learning and classification.
• Score: 52.5745217752147
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Facial age estimation is an important yet very challenging problem in computer vision. To improve the performance of facial age estimation, we first formulate a simple standard baseline and build a much strong one by collecting the tricks in pre-training, data augmentation, model architecture, and so on. Compared with the standard baseline, the proposed one significantly decreases the estimation errors. Moreover, long-tailed recognition has been an important topic in facial age datasets, where the samples often lack on the elderly and children. To train a balanced age estimator, we propose a two-stage training method named Long-tailed Age Estimation (LAE), which decouples the learning procedure into representation learning and classification. The effectiveness of our approach has been demonstrated on the dataset provided by organizers of Guess The Age Contest 2021.

Related papers

• P-Age: Pexels Dataset for Robust Spatio-Temporal Apparent Age Classification [0.7234862895932991]
  AgeFormer utilizes information on the dynamics of the entire body face-based methods for age classification. To fill the gap in predicting age in real-world situations from videos, we construct a video dataset called Pexels Age. The proposed method achieves superior results compared to existing face-based age estimation methods.
  arXiv  Detail & Related papers  (2023-11-04T15:23:21Z)
• General vs. Long-Tailed Age Estimation: An Approach to Kill Two Birds with One Stone [48.849311629912734]
  We propose a simple, effective, and flexible training paradigm named GLAE, which is two-fold. Our GLAE provides a surprising improvement on Morph II, reaching the lowest MAE and CMAE of 1.14 and 1.27 years, respectively.
  arXiv  Detail & Related papers  (2023-07-19T16:51:59Z)
• MetaAge: Meta-Learning Personalized Age Estimators [94.73054410570037]
  We propose a meta-learning method named MetaAge for age estimation. Specifically, we introduce a personalized estimator meta-learner, which takes identity features as the input and outputs the parameters of customized estimators. In this way, our method learns the meta knowledge without the above requirements and seamlessly transfers the learned meta knowledge to the test set.
  arXiv  Detail & Related papers  (2022-07-12T03:53:42Z)
• FP-Age: Leveraging Face Parsing Attention for Facial Age Estimation in the Wild [50.8865921538953]
  We propose a method to explicitly incorporate facial semantics into age estimation. We design a face parsing-based network to learn semantic information at different scales. We show that our method consistently outperforms all existing age estimation methods.
  arXiv  Detail & Related papers  (2021-06-21T14:31:32Z)
• using multiple losses for accurate facial age estimation [6.851375622634309]
  We propose a simple yet effective approach for age estimation, which improves the performance compared to classification-based methods. We validate the Age-Granularity-Net framework on the CVPR Chalearn 2016 dataset, and extensive experiments show that the proposed approach can reduce the prediction error compared to any individual loss.
  arXiv  Detail & Related papers  (2021-06-17T11:18:16Z)
• Continuous Face Aging via Self-estimated Residual Age Embedding [8.443742714362521]
  We propose a unified network structure that embeds a linear age estimator into a GAN-based model. The embedded age estimator is trained jointly with the encoder and decoder to estimate the age of a face image. The personalized target age embedding is synthesized by incorporating both personalized residual age embedding of the current age and exemplar-face aging basis of the target age.
  arXiv  Detail & Related papers  (2021-04-30T18:06:17Z)
• PFA-GAN: Progressive Face Aging with Generative Adversarial Network [19.45760984401544]
  This paper proposes a novel progressive face aging framework based on generative adversarial network (PFA-GAN) The framework can be trained in an end-to-end manner to eliminate accumulative artifacts and blurriness. Extensively experimental results demonstrate superior performance over existing (c)GANs-based methods.
  arXiv  Detail & Related papers  (2020-12-07T05:45:13Z)
• Age Gap Reducer-GAN for Recognizing Age-Separated Faces [72.26969872180841]
  We propose a novel algorithm for matching faces with temporal variations caused due to age progression. The proposed generative adversarial network algorithm is a unified framework that combines facial age estimation and age-separated face verification.
  arXiv  Detail & Related papers  (2020-11-11T16:43:32Z)
• Enhancing Facial Data Diversity with Style-based Face Aging [59.984134070735934]
  In particular, face datasets are typically biased in terms of attributes such as gender, age, and race. We propose a novel, generative style-based architecture for data augmentation that captures fine-grained aging patterns. We show that the proposed method outperforms state-of-the-art algorithms for age transfer.
  arXiv  Detail & Related papers  (2020-06-06T21:53:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.