Multi-label field adaptive method based on prompt driving

By generating multi-dimensional semantic descriptions and dynamic label association graphs using a large language model, the problems of label relevance solidification and insufficient semantic representation in multi-label domain adaptation are solved. This achieves synergistic alignment of cross-domain features and label relevance, and improves the model's generalization ability in unlabeled target domains.

CN121838151APending Publication Date: 2026-04-10NANJING UNIV OF POSTS & TELECOMM
0 Cites 2 Cited by

Patent Information

Application Number
CN202511990934.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-12-26
Publication Date
2026-04-10

AI Technical Summary

Technical Problem

Existing multi-label domain adaptation methods suffer from problems such as fixed label relevance assumptions, insufficient category semantic representation, and independent learning processes, leading to performance degradation in cross-domain scenarios.

Method used

A large language model is used to generate multi-dimensional semantic descriptions, construct a dynamic label association graph, and synchronize the feature distribution and label relevance under a unified framework. The model is optimized through semantic reconstruction and graph convolutional network.

Benefits of technology

It significantly improves the model's generalization ability in unlabeled target domains, solves the problem of sparsity and granularity mismatch in cross-domain category semantic representation, enhances the model's adaptability and robustness, and simplifies the training process.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a multi-label field adaptive method based on prompt driving, which belongs to the technical field of computer vision and comprises the following steps: generating multi-dimensional semantic text description containing visual attributes, semantic levels and category names of common scenes for each type; embedding the semantic text description into an optimizable category vector, and embedding the optimized category vector into a CLIP text prompt; extracting and projecting multi-layer style statistical characteristics of the image, and synchronously realizing image-text cross-modal alignment and source-target domain distribution alignment in a frame through a cross-domain style mapping network and various alignment losses; semantic priori knowledge of CLIP is combined with a label co-occurrence mode of a source domain, so that the model can sense and adapt to a possibly changed label dependency relationship in a target domain; performing semantic propagation on label embedding by using a graph convolutional network; the whole system is jointly optimized through a multi-task loss function, and end-to-end cross-domain multi-label classification is achieved.
Need to check novelty before this filing date? Find Prior Art