# Learning from Ambiguously Labeled Face Images

arXiv: https://arxiv.org/abs/1702.04455 · HTML: https://mlsanity.com/paper/1702.04455/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Feb 2017.

## Built on by (most cited first, 29 of 29)

- [Leveraged Weighted Loss for Partial Label Learning](https://mlsanity.com/paper/2106.05731/) (2021)
- [Instance-Dependent Partial Label Learning](https://mlsanity.com/paper/2110.12911/) (2021)
- [SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning](https://mlsanity.com/paper/2209.10365/) (2022)
- [Long-Tailed Partial Label Learning via Dynamic Rebalancing](https://mlsanity.com/paper/2302.05080/) (2023)
- [PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning](https://mlsanity.com/paper/2201.08984/) (2022)
- [On the Robustness of Average Losses for Partial-Label Learning](https://mlsanity.com/paper/2106.06152/) (2021)
- [Realistic Evaluation of Deep Partial-Label Learning Algorithms](https://mlsanity.com/paper/2502.10184/) (2025)
- [CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning](https://mlsanity.com/paper/2303.10365/) (2023)
- [Towards Effective Visual Representations for Partial-Label Learning](https://mlsanity.com/paper/2305.06080/) (2023)
- [Learning with Partial Labels from Semi-supervised Perspective](https://mlsanity.com/paper/2211.13655/) (2022)
- [ALIM: Adjusting Label Importance Mechanism for Noisy Partial Label Learning](https://mlsanity.com/paper/2301.12077/) (2023)
- [Algorithmic Censoring in Dynamic Learning Systems](https://mlsanity.com/paper/2305.09035/) (2023)
- [IRNet: Iterative Refinement Network for Noisy Partial Label Learning](https://mlsanity.com/paper/2211.04774/) (2022)
- [Unreliable Partial Label Learning with Recursive Separation](https://mlsanity.com/paper/2302.09891/) (2023)
- [Partial-Label Regression](https://mlsanity.com/paper/2306.08968/) (2023)
- [Controller-Guided Partial Label Consistency Regularization with Unlabeled Data](https://mlsanity.com/paper/2210.11194/) (2022)
- [Robust Representation Learning for Unreliable Partial Label Learning](https://mlsanity.com/paper/2308.16718/) (2023)
- [Tuning the Right Foundation Models is What you Need for Partial Label Learning](https://mlsanity.com/paper/2506.05027/) (2025)
- [ProPaLL: Probabilistic Partial Label Learning](https://mlsanity.com/paper/2208.09931/) (2022)
- [Pseudo-labelling meets Label Smoothing for Noisy Partial Label Learning](https://mlsanity.com/paper/2402.04835/) (2024)
- [Weakly-Supervised Contrastive Learning for Imprecise Class Labels](https://mlsanity.com/paper/2505.22028/) (2025)
- [Decompositional Generation Process for Instance-Dependent Partial Label Learning](https://mlsanity.com/paper/2204.03845/) (2022)
- [AsyCo: An Asymmetric Dual-task Co-training Model for Partial-label Learning](https://mlsanity.com/paper/2407.15036/) (2024)
- [An Unbiased Risk Estimator for Partial Label Learning with Augmented Classes](https://mlsanity.com/paper/2409.19600/) (2024)
- [Reduction-based Pseudo-label Generation for Instance-dependent Partial Label Learning](https://mlsanity.com/paper/2410.20797/) (2024)
- [Partial Label Clustering](https://mlsanity.com/paper/2505.03207/) (2025)
- [Mitigating Instance Entanglement in Instance-Dependent Partial Label Learning](https://mlsanity.com/paper/2603.04825/) (2026)
- [A proximal subgradient method for nonconvex stochastic optimization under the Kurdyka-Lojasiewicz condition](https://mlsanity.com/paper/2608.05460/) (2026)
- [Recent advances in weakly supervised learning: New supervision paradigms, assumption relaxations, and practical solutions](https://mlsanity.com/paper/2608.06896/) (2026)

## Abstract (arXiv)

Learning a classifier from ambiguously labeled face images is challenging since training images are not always explicitly-labeled. For instance, face images of two persons in a news photo are not explicitly labeled by their names in the caption. We propose a Matrix Completion for Ambiguity Resolution (MCar) method for predicting the actual labels from ambiguously labeled images. This step is followed by learning a standard supervised classifier from the disambiguated labels to classify new images. To prevent the majority labels from dominating the result of MCar, we generalize MCar to a weighted MCar (WMCar) that handles label imbalance. Since WMCar outputs a soft labeling vector of reduced ambiguity for each instance, we can iteratively refine it by feeding it as the input to WMCar. Nevertheless, such an iterative implementation can be affected by the noisy soft labeling vectors, and thus the performance may degrade. Our proposed Iterative Candidate Elimination (ICE) procedure makes the iterative ambiguity resolution possible by gradually eliminating a portion of least likely candidates in ambiguously labeled face. We further extend MCar to incorporate the labeling constraints between instances when such prior knowledge is available. Compared to existing methods, our approach demonstrates improvement on several ambiguously labeled datasets.