# MiVOLO: Multi-input Transformer for Age and Gender Estimation

arXiv: https://arxiv.org/abs/2307.04616 · HTML: https://mlsanity.com/paper/2307.04616/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 46 references that are in the map.
- First posted on arXiv 10 Jul 2023.

## Builds on (most cited first, 20 of 20)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [XCiT: Cross-Covariance Image Transformers](https://mlsanity.com/paper/2106.09681/) (2021)
- [Compacting, Picking and Growing for Unforgetting Continual Learning](https://mlsanity.com/paper/1910.06562/) (2019)
- [VOLO: Vision Outlooker for Visual Recognition](https://mlsanity.com/paper/2106.13112/) (2021)
- [Delving into Deep Imbalanced Regression](https://mlsanity.com/paper/2102.09554/) (2021)
- [Rank consistent ordinal regression for neural networks with application to age estimation](https://mlsanity.com/paper/1901.07884/) (2019)
- [Moving Window Regression: A Novel Approach to Ordinal Regression](https://mlsanity.com/paper/2203.13122/) (2022)
- [FP-Age: Leveraging Face Parsing Attention for Facial Age Estimation in the Wild](https://mlsanity.com/paper/2106.11145/) (2021)
- [Fine-Grained Age Estimation in the wild with Attention LSTM Networks](https://mlsanity.com/paper/1805.10445/) (2018)
- [Investigating Bias in Deep Face Analysis: The KANFace Dataset and Empirical Study](https://mlsanity.com/paper/2005.07302/) (2020)
- [Deep Ordinal Regression with Label Diversity](https://mlsanity.com/paper/2006.15864/) (2020)
- [Age and Gender Prediction From Face Images Using Attentional Convolutional Network](https://mlsanity.com/paper/2010.03791/) (2020)
- [Deep Ordinal Regression using Optimal Transport Loss and Unimodal Output Probabilities](https://mlsanity.com/paper/2011.07607/) (2020)
- [Generalizing MLPs With Dropouts, Batch Normalization, and Skip Connections](https://mlsanity.com/paper/2108.08186/) (2021)

## Built on by (most cited first, 30 of 42)

- [FaceXFormer: A Unified Transformer for Facial Analysis](https://mlsanity.com/paper/2403.12960/) (2024)
- [Face-MLLM: A Large Face Perception Model](https://mlsanity.com/paper/2410.20717/) (2024)
- [Beyond Specialization: Assessing the Capabilities of MLLMs in Age and Gender Estimation](https://mlsanity.com/paper/2403.02302/) (2024)
- [Image-Perfect Imperfections: Safety, Bias, and Authenticity in the Shadow of Text-To-Image Model Evolution](https://mlsanity.com/paper/2408.17285/) (2024)
- [FaVChat: Hierarchical Prompt-Query Guided Facial Video Understanding with Data-Efficient GRPO](https://mlsanity.com/paper/2503.09158/) (2025)
- [Out of the box age estimation through facial imagery: A Comprehensive Benchmark of Vision-Language Models vs. out-of-the-box Traditional Architectures](https://mlsanity.com/paper/2602.07815/) (2026)
- [Identifying Drivers of Predictive Aleatoric Uncertainty](https://mlsanity.com/paper/2312.07252/) (2023)
- [Chain-of-Thought Prompting for Demographic Inference with Large Multimodal Models](https://mlsanity.com/paper/2405.15687/) (2024)
- [Do Existing Testing Tools Really Uncover Gender Bias in Text-to-Image Models?](https://mlsanity.com/paper/2501.15775/) (2025)
- [On the rankability of visual embeddings](https://mlsanity.com/paper/2507.03683/) (2025)
- [Human Pose Descriptions and Subject-Focused Attention for Improved Zero-Shot Transfer in Human-Centric Classification Tasks](https://mlsanity.com/paper/2403.06904/) (2024)
- [HaGRIDv2: 1M Images for Static and Dynamic Hand Gesture Recognition](https://mlsanity.com/paper/2412.01508/) (2024)
- [GroupFace: Imbalanced Age Estimation Based on Multi-hop Attention Graph Convolutional Network and Group-aware Margin Optimization](https://mlsanity.com/paper/2412.11450/) (2024)
- [FaceInsight: A Multimodal Large Language Model for Face Perception](https://mlsanity.com/paper/2504.15624/) (2025)
- [From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging](https://mlsanity.com/paper/2506.20977/) (2025)
- [AgeBooth: Controllable Facial Aging and Rejuvenation via Diffusion Models](https://mlsanity.com/paper/2510.05715/) (2025)
- [Towards Metric-Aware Multi-Person Mesh Recovery by Jointly Optimizing Human Crowd in Camera Space](https://mlsanity.com/paper/2511.13282/) (2025)
- [Ranking-aware adapter for text-driven image ordering with CLIP](https://mlsanity.com/paper/2412.06760/) (2024)
- [Logos as a Well-Tempered Pre-train for Sign Language Recognition](https://mlsanity.com/paper/2505.10481/) (2025)
- [A Manually Annotated Image-Caption Dataset for Detecting Children in the Wild](https://mlsanity.com/paper/2506.10117/) (2025)
- [Underage Detection through a Multi-Task and MultiAge Approach for Screening Minors in Unconstrained Imagery](https://mlsanity.com/paper/2506.10689/) (2025)
- [VIBE: Visual Instruction Based Editor](https://mlsanity.com/paper/2601.02242/) (2026)
- [Evaluating Epistemic Uncertainty: Beyond OOD Detection and Active Learning](https://mlsanity.com/paper/2607.14817/) (2026)
- [Enhancing User-Centric Privacy Protection: An Interactive Framework through Diffusion Models and Machine Unlearning](https://mlsanity.com/paper/2409.03326/) (2024)
- [LRA-GNN: Latent Relation-Aware Graph Neural Network with Initial and Dynamic Residual for Facial Age Estimation](https://mlsanity.com/paper/2502.05423/) (2025)
- [Evaluating Facial Expression Recognition Datasets for Deep Learning: A Benchmark Study with Novel Similarity Metrics](https://mlsanity.com/paper/2503.20428/) (2025)
- [ExpertGen: Training-Free Expert Guidance for Controllable Text-to-Face Generation](https://mlsanity.com/paper/2505.17256/) (2025)
- [Overcoming Occlusions in the Wild: A Multi-Task Age Head Approach to Age Estimation](https://mlsanity.com/paper/2506.13445/) (2025)
- [Bukva: Russian Sign Language Alphabet](https://mlsanity.com/paper/2410.08675/) (2024)
- [DIPSER: A Dataset for In-Person Student Engagement Recognition in the Wild](https://mlsanity.com/paper/2502.20209/) (2025)

## Abstract (arXiv)

Age and gender recognition in the wild is a highly challenging task: apart from the variability of conditions, pose complexities, and varying image quality, there are cases where the face is partially or completely occluded. We present MiVOLO (Multi Input VOLO), a straightforward approach for age and gender estimation using the latest vision transformer. Our method integrates both tasks into a unified dual input/output model, leveraging not only facial information but also person image data. This improves the generalization ability of our model and enables it to deliver satisfactory results even when the face is not visible in the image. To evaluate our proposed model, we conduct experiments on four popular benchmarks and achieve state-of-the-art performance, while demonstrating real-time processing capabilities. Additionally, we introduce a novel benchmark based on images from the Open Images Dataset. The ground truth annotations for this benchmark have been meticulously generated by human annotators, resulting in high accuracy answers due to the smart aggregation of votes. Furthermore, we compare our model's age recognition performance with human-level accuracy and demonstrate that it significantly outperforms humans across a majority of age ranges. Finally, we grant public access to our models, along with the code for validation and inference. In addition, we provide extra annotations for used datasets and introduce our new benchmark.