Beyond Specialization: Assessing the Capabilities of MLLMs in Age and Gender Estimation

4 Mar 2024  ·  Maksim Kuprashevich, Grigorii Alekseenko, Irina Tolstykh ·

Multimodal Large Language Models (MLLMs) have recently gained immense popularity. Powerful commercial models like ChatGPT-4V and Gemini, as well as open-source ones such as LLaVA, are essentially general-purpose models and are applied to solve a wide variety of tasks, including those in computer vision. These neural networks possess such strong general knowledge and reasoning abilities that they have proven capable of working even on tasks for which they were not specifically trained. We compared the capabilities of the most powerful MLLMs to date: ShareGPT4V, ChatGPT, LLaVA-Next in a specialized task of age and gender estimation with our state-of-the-art specialized model, MiVOLO. We also updated MiVOLO and provide details and new metrics in this article. This comparison has yielded some interesting results and insights about the strengths and weaknesses of the participating models. Furthermore, we attempted various ways to fine-tune the ShareGPT4V model for this specific task, aiming to achieve state-of-the-art results in this particular challenge. Although such a model would not be practical in production, as it is incredibly expensive compared to a specialized model like MiVOLO, it could be very useful in some tasks, like data annotation.

PDF Abstract

Results from the Paper


 Ranked #1 on Age And Gender Classification on Adience Gender (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Age And Gender Classification Adience Age MiVOLO-V2 Accuracy (5-fold) 69.43 # 2
Age And Gender Classification Adience Gender MiVOLO-V2 Accuracy (5-fold) 97.39 # 1
Age Estimation CACD MiVOLO-V2 MAE 3.89 # 1
Facial Attribute Classification FairFace MiVOLO-V2 gender-top1 97.5 # 1
age-top1 62.28 # 1
Age Estimation IMDB-Clean MiVOLO-V2 Average mean absolute error 3.97 # 1
Gender Prediction LAGENDA MiVOLO-V2 Accuracy 97.99 # 1
Age Estimation LAGENDA MiVOLO-V2 MAE 3.65 # 1
Age and Gender Estimation LAGENDA age MiVOLO-V2 MAE 3.65 # 1
CS@5 74.48 # 1
Age and Gender Estimation LAGENDA gender MiVOLO-V2 CS@5 74.48 # 1

Methods


No methods listed for this paper. Add relevant methods here