Stage-wise Adaptive Label Distribution for Facial Age Estimation

• URL: http://arxiv.org/abs/2509.00450v1
• Date: Sat, 30 Aug 2025 10:45:24 GMT
• Title: Stage-wise Adaptive Label Distribution for Facial Age Estimation
• Abstract summary: We propose a Stage-wise Adaptive Label Distribution Learning (SA-LDL) algorithm for age estimation.<n>SA-LDL effectively captures the complex and structured nature of label ambiguity, leading to more accurate and robust age estimation.<n>Experiments demonstrate that SA-LDL achieves competitive performance, with MAE of 1.74 and 2.15 on the MORPH-II and FG-NET datasets.
• Score: 21.55166602124972
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Label ambiguity poses a significant challenge in age estimation tasks. Most existing methods address this issue by modeling correlations between adjacent age groups through label distribution learning. However, they often overlook the varying degrees of ambiguity present across different age stages. In this paper, we propose a Stage-wise Adaptive Label Distribution Learning (SA-LDL) algorithm, which leverages the observation -- revealed through our analysis of embedding similarities between an anchor and all other ages -- that label ambiguity exhibits clear stage-wise patterns. By jointly employing stage-wise adaptive variance modeling and weighted loss function, SA-LDL effectively captures the complex and structured nature of label ambiguity, leading to more accurate and robust age estimation. Extensive experiments demonstrate that SA-LDL achieves competitive performance, with MAE of 1.74 and 2.15 on the MORPH-II and FG-NET datasets.

Related papers

• From Inference to Adaptation: A Unified Optimal Transport View of Vision Language Model [81.67708143891319]
  Vision-language models (VLMs) have demonstrated remarkable zero-shot capabilities yet remain sensitive to real-world distribution shifts during inference.<n>We bridge the detached objectives of inference and adaptation forVLMs, and propose a principled VLM TTA method called algname.<n>Experiments demonstrate the effectiveness and efficiency of our methods, outperforming the best-performing methods by up to 7% with state-of-the-art efficiency.
  arXiv  Detail & Related papers  (2026-08-18T21:44:32Z)
• DiCaP: Distribution-Calibrated Pseudo-labeling for Semi-Supervised Multi-Label Learning [83.94574004953346]
  Semi-supervised multi-label learning aims to leverage unlabeled data to improve the model's performance.<n>Most existing methods assign equal weights to all pseudo-labels regardless of their quality.<n>We propose Distribution-Calibrated Pseudo-labeling (DiCaP), a correctness-aware framework that estimates posterior precision to calibrate pseudo-label weights.
  arXiv  Detail & Related papers  (2025-11-25T11:55:02Z)
• From Age Estimation to Age-Invariant Face Recognition: Generalized Age Feature Extraction Using Order-Enhanced Contrastive Learning [23.817867981093382]
  Generalized age feature extraction is crucial for age-related facial analysis tasks.<n>We propose a novel contrastive learning framework designed explicitly for ordinal attributes like age.<n>Our proposed method achieves comparable results to state-of-the-art methods on various benchmark datasets.
  arXiv  Detail & Related papers  (2025-01-03T11:23:52Z)
• Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition [50.61991746981703]
  Current state-of-the-art LTSSL approaches rely on high-quality pseudo-labels for large-scale unlabeled data. This paper introduces a novel probabilistic framework that unifies various recent proposals in long-tail learning. We introduce a continuous contrastive learning method, CCL, extending our framework to unlabeled data using reliable and smoothed pseudo-labels.
  arXiv  Detail & Related papers  (2024-10-08T15:06:10Z)
• Exploring Contrastive Learning for Long-Tailed Multi-Label Text Classification [48.81069245141415]
  We introduce a novel contrastive loss function for multi-label text classification. It attains Micro-F1 scores that either match or surpass those obtained with other frequently employed loss functions. It demonstrates a significant improvement in Macro-F1 scores across three multi-label datasets.
  arXiv  Detail & Related papers  (2024-04-12T11:12:16Z)
• Maturity-Aware Active Learning for Semantic Segmentation with Hierarchically-Adaptive Sample Assessment [18.65352271757926]
  "Maturity-Aware Distribution Breakdown-based Active Learning" (MADBAL) is an AL method that takes into account the different "sample" definitions jointly. MADBAL makes significant performance leaps even in the early AL stage, hence reducing the training burden significantly. It outperforms state-of-the-art methods on Cityscapes and PASCAL VOC datasets as verified in our experiments.
  arXiv  Detail & Related papers  (2023-08-28T21:13:04Z)
• Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection [98.66771688028426]
  We propose a Ambiguity-Resistant Semi-supervised Learning (ARSL) for one-stage detectors. Joint-Confidence Estimation (JCE) is proposed to quantifies the classification and localization quality of pseudo labels. ARSL effectively mitigates the ambiguities and achieves state-of-the-art SSOD performance on MS COCO and PASCAL VOC.
  arXiv  Detail & Related papers  (2023-03-27T07:46:58Z)
• SVLDL: Improved Speaker Age Estimation Using Selective Variance Label Distribution Learning [24.57668015470307]
  We propose selective variance label distribution learning (SVLDL) method to adapt the variance of different age distributions. Model uses WavLM as the speech feature extractor and adds the auxiliary task of gender recognition to further improve the performance. Experiments show that the model achieves state-of-the-art performance on all aspects of the NIST SRE08-10 and a real-world datasets.
  arXiv  Detail & Related papers  (2022-10-18T01:34:31Z)
• Adversarial Dual-Student with Differentiable Spatial Warping for Semi-Supervised Semantic Segmentation [70.2166826794421]
  We propose a differentiable geometric warping to conduct unsupervised data augmentation. We also propose a novel adversarial dual-student framework to improve the Mean-Teacher. Our solution significantly improves the performance and state-of-the-art results are achieved on both datasets.
  arXiv  Detail & Related papers  (2022-03-05T17:36:17Z)
• Towards Speaker Age Estimation with Label Distribution Learning [26.12240876065871]
  We utilize the ambiguous information among the age labels, convert each age label into a discrete label distribution and leverage the label distribution learning (LDL) method to fit the data. Our method naturally combines the age classification and regression approaches, which enhances the robustness of our method. We conduct experiments on the public NIST SRE08-10 dataset and a real-world dataset, which exhibit that our method outperforms baseline methods by a relatively large margin.
  arXiv  Detail & Related papers  (2022-02-23T11:11:58Z)
• Semi-supervised Long-tailed Recognition using Alternate Sampling [95.93760490301395]
  Main challenges in long-tailed recognition come from the imbalanced data distribution and sample scarcity in its tail classes. We propose a new recognition setting, namely semi-supervised long-tailed recognition. We demonstrate significant accuracy improvements over other competitive methods on two datasets.
  arXiv  Detail & Related papers  (2021-05-01T00:43:38Z)
• PML: Progressive Margin Loss for Long-tailed Age Classification [9.020103398777653]
  We propose a progressive margin loss (PML) approach for unconstrained facial age classification. Our PML aims to adaptively refine the age label pattern by enforcing a couple of margins.
  arXiv  Detail & Related papers  (2021-03-03T02:47:09Z)
• Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization [55.278153228758434]
  Real-world datasets are heteroskedastic and imbalanced. Addressing heteroskedasticity and imbalance simultaneously is under-explored. We propose a data-dependent regularization technique for heteroskedastic datasets.
  arXiv  Detail & Related papers  (2020-06-29T01:09:50Z)
• ESL: Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic Segmentation [35.03150829133562]
  We propose Entropy-guided Self-supervised Learning, leveraging entropy as the confidence indicator for producing more accurate pseudo-labels. On different UDA benchmarks, ESL consistently outperforms strong SSL baselines and achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2020-06-15T18:10:09Z)

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.