Incremental learning method and apparatus for large vision-language model for autonomous driving

US12400124B1 · kind B1 · utility

Assignee

• Beijing University of Chemical Technology · CN

Inventors

• Zhiwei Li · Lo Wu, CN
• Jingshuo Liu · Beijing, CN
• Peiran Chen · Beijing, CN
• Zihao Wu · Beijing, CN
• Xintao WU · Beijing, CN
• Kunfeng Wang · Tangxia, CN
• Tianyu Shen · Beijing, CN
• Li Wang · Beijing, CN
• Qifan Tan · Beijing, CN
• Wei Zhang · Shanghai, CN

Key dates

• Filing date: Feb 13, 2025
• Grant date: Aug 26, 2025
• Expiry date: Feb 13, 2045

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N3/08
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

An incremental learning method and apparatus for a large Vision-Language Model for autonomous driving are provided. The incremental learning method includes: expanding a first training sample set to obtain a second training sample set, wherein the second training sample set includes a plurality of image samples annotated with road scene targets; inserting a plurality of fine-tuning sub-networks respectively into specified positions in a first large Vision-Language Model to generate a second large Vision-Language Model; processing the image samples in the second training sample set using the second large Vision-Language Model to obtain a target prediction result; calculating a loss value using the target prediction result and a target annotation result; and preserving parameters of the first large Vision-Language Model unchanged, and updating parameters of the fine-tuning sub-networks using the loss value.