{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/beyond-specialization-assessing-the-1","title":"Beyond Specialization: Assessing the Capabilities of MLLMs in Age and Gender Estimation","arxiv_id":"2403.02302","date":"2024-03-04","proceeding":null,"authors":["Maksim Kuprashevich","Grigorii Alekseenko","Irina Tolstykh"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2403.02302v4","url_pdf":"https://arxiv.org/pdf/2403.02302v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"beyond-specialization-assessing-the-1","repo_url":"https://github.com/wildchlamydia/mivolo","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"age-and-gender-classification","task_name":"Age And Gender Classification"},{"task_slug":"age-estimation","task_name":"Age Estimation"},{"task_slug":"age-and-gender-estimation","task_name":"Age and Gender Estimation"},{"task_slug":"facial-attribute-classification","task_name":"Facial Attribute Classification"},{"task_slug":"gender-prediction","task_name":"Gender Prediction"},{"task_slug":"general-knowledge","task_name":"General Knowledge"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/age-and-gender-classification-on-adience-age","task":"Age And Gender Classification","dataset":"Adience Age","model":"MiVOLO-V2","rank_in_archive_order":2,"of":16,"metrics":{"Accuracy (5-fold)":"69.43"},"uses_additional_data":true},{"leaderboard":"/sota/age-and-gender-classification-on-adience","task":"Age And Gender Classification","dataset":"Adience Gender","model":"MiVOLO-V2","rank_in_archive_order":1,"of":10,"metrics":{"Accuracy (5-fold)":"97.39"},"uses_additional_data":true},{"leaderboard":"/sota/age-estimation-on-cacd","task":"Age Estimation","dataset":"CACD","model":"MiVOLO-V2","rank_in_archive_order":1,"of":13,"metrics":{"MAE":"3.89"},"uses_additional_data":true},{"leaderboard":"/sota/age-estimation-on-imdb-clean","task":"Age Estimation","dataset":"IMDB-Clean","model":"MiVOLO-V2","rank_in_archive_order":1,"of":4,"metrics":{"Average mean absolute error":"3.97"},"uses_additional_data":true},{"leaderboard":"/sota/age-estimation-on-lagenda","task":"Age Estimation","dataset":"LAGENDA","model":"MiVOLO-V2","rank_in_archive_order":1,"of":2,"metrics":{"MAE":"3.65"},"uses_additional_data":true},{"leaderboard":"/sota/age-and-gender-estimation-on-lagenda-age","task":"Age and Gender Estimation","dataset":"LAGENDA age","model":"MiVOLO-V2","rank_in_archive_order":1,"of":2,"metrics":{"CS@5":"74.48","MAE":"3.65"},"uses_additional_data":true},{"leaderboard":"/sota/age-and-gender-estimation-on-lagenda-gender","task":"Age and Gender Estimation","dataset":"LAGENDA gender","model":"MiVOLO-V2","rank_in_archive_order":2,"of":2,"metrics":{"CS@5":"74.48"},"uses_additional_data":false},{"leaderboard":"/sota/facial-attribute-classification-on-fairface","task":"Facial Attribute Classification","dataset":"FairFace","model":"MiVOLO-V2","rank_in_archive_order":1,"of":3,"metrics":{"age-top1":"62.28","gender-top1":"97.5"},"uses_additional_data":true},{"leaderboard":"/sota/gender-prediction-on-lagenda","task":"Gender Prediction","dataset":"LAGENDA","model":"MiVOLO-V2","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"97.99"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}