计算机科学
分类器(UML)
人工智能
机器学习
领域(数学分析)
透视图(图形)
训练集
面子(社会学概念)
任务分析
任务(项目管理)
结构化预测
过程(计算)
标记数据
领域知识
多任务学习
绩效改进
数据建模
数据挖掘
迭代和增量开发
面部识别系统
特征提取
作者
Huali Xu,Li Liu,Tianpeng Liu,Shuaifeng Zhi,Shuzhou Sun,Ming‐Ming Cheng
标识
DOI:10.1109/tpami.2025.3610039
摘要
Existing cross-domain few-shot learning (CDFSL) methods, which develop training strategies in the source domain to enhance model transferability, face challenges when applied to large-scale pre-trained models (LMs), as their source domains and training strategies are not accessible. Besides, fine-tuning LMs specifically for CDFSL requires substantial computational resources, which limits their practicality. Therefore, this paper investigates the source-free CDFSL (SF-CDFSL) problem to solve the few-shot learning (FSL) task in target domain using only a pre-trained model and a few target samples, without requiring source data or training strategies. However, the inaccessibility of source data prevents explicitly reducing the domain gaps between the source and target. To tackle this challenge, this paper proposes a novel approach, Step-wise Distribution-aligned Style Prompt Tuning (StepSPT), to implicitly narrow the domain gaps from the perspective of prediction distribution optimization. StepSPT initially proposes a style prompt that adjusts the target samples to mirror the expected distribution. Furthermore, StepSPT tunes the style prompt and classifier by exploring a dual-phase optimization process (external and internal processes). In the external process, a step-wise distribution alignment strategy is introduced to tune the proposed style prompt by factorizing the prediction distribution optimization problem into the multi-step distribution alignment problem. In the internal process, the classifier is updated via standard cross-entropy loss. Evaluation on 5 datasets illustrates the superiority of StepSPT over existing prompt tuning-based methods and state-of-the-art methods (SOTAs). Furthermore, ablation studies and performance analyzes highlight the efficacy of StepSPT.
科研通智能强力驱动
Strongly Powered by AbleSci AI