MUMBAI, India, Sept. 26 -- Intellectual Property India has published a patent application (202421021527 A) filed by Tata Consultancy Services Limited, Maharashtra, on March 21, 2024, for 'method and system for incremental learning based fashion attribute extraction.'
Inventor(s) include Kanade, Aditya; Patwardhan, Manasi Samarth; Patidar, Mayur; Vig, Lovekesh; and Vasudevan, Bagya Lakshmi.
The application for the patent was published on Sept. 26, under issue no. 39/2025.
According to the abstract released by the Intellectual Property India: "Model based approaches that are currently being used for Fashion Attribute Extraction (FAE) have the disadvantage that they are trained on static ontology, hence making them incapable of accommodating changes in the fashion industry, due to absence of an incremental dataset for training. Embodiments disclosed herein provide a method and system for incremental learning based fashion attribute extraction. The system generates prompts to train a data model as an incremental learning, causing learning of an evolving ontology with respect to fashion attributes, while retaining information in the pre-existed database. The data model thus generated is used for fashion attribute extraction."
Disclaimer: Curated by HT Syndication.
