当语义饱和或涌现时：无源跨域小样本学习中的适配条件语义效用
When Semantics Saturate or Emerge: Adaptation-Conditional Semantic Utility in Source-Free Cross-Domain Few-Shot Learning
浏览论文内容
中文总结 AI 辅助
该研究针对无源跨域小样本学习，发现零样本提示质量无法完全代表适配锚点质量，揭示了语义饱和与涌现两种模式，为评估语言提供了新方向。
中文摘要 AI 辅助
在无源跨域小样本学习（SF-CDFSL）中，语言描述通常根据冻结的视觉-语言模型获得的零样本准确率进行选择。本文探究该排序在目标域视觉适配后是否仍然有效。在严格配对协议下，我们对比了通用类名模板与固定详细类描述在视觉低秩适配（LoRA）前后，于EuroSAT、CropDisease、ISIC和ChestX数据集上的表现。令δ₀和δ_LoRA分别表示适配前后详细描述与基础描述的准确率差值。两种反复出现的模式得以显现：在“语义饱和”模式中，δ₀>0但0<δ_LoRA≪δ₀，如EuroSAT和CropDisease数据集上，初始8.13-21.54个百分点的增益在LoRA后收缩至0.69-2.96个百分点；在“语义涌现”模式中，δ₀≤0但δ_LoRA>0，如ISIC和ChestX数据集上，详细描述仅在视觉表征更新后才更有用。训练轨迹与样本级分解显示，饱和主要由基础-LoRA恢复了详细语义已解决的错误导致，而涌现则与预测更替及新形成的仅详细描述的正确决策相关。无固定点的打乱语义对照、第二种CLIP主干及多个随机种子均支持该普遍模式，同时确定ChestX 1-shot为弱边界案例。这些发现表明，零样本提示质量是适配锚点质量的不完整代理，并推动在适配边界两侧评估语言。
英文摘要
Language descriptions in source-free cross-domain few-shot learning (SF-CDFSL) are often selected according to zero-shot accuracy obtained with a frozen vision--language model. This paper asks whether that ranking remains valid after target-domain visual adaptation. Under a strictly paired protocol, we compare a generic class-name template with fixed detailed class descriptions before and after visual Low-Rank Adaptation (LoRA) on EuroSAT, CropDisease, ISIC, and ChestX. Let $\deltazero$ and $\deltalora$ denote the Detailed-minus-Base accuracy before and after adaptation, respectively. Two recurring regimes emerge. In \emph{semantic saturation}, $\deltazero>0$ but $0<\deltalora\ll\deltazero$: on EuroSAT and CropDisease, initial gains of 8.13--21.54 percentage points contract to 0.69--2.96 points after LoRA. In \emph{semantic emergence}, $\deltazero\leq0$ but $\deltalora>0$: on ISIC and ChestX, detailed descriptions become more useful only after the visual representation is updated. Training trajectories and sample-level decomposition show that saturation is driven mainly by Base-LoRA recovering errors already solved by detailed semantics, whereas emergence is associated with prediction turnover and newly formed Detailed-only correct decisions. Fixed-point-free shuffled-semantic controls, a second CLIP backbone, and multiple random seeds support the broad pattern while identifying ChestX 1-shot as a weak boundary case. These findings establish that zero-shot prompt quality is an incomplete proxy for adaptation-anchor quality and motivate evaluating language on both sides of the adaptation boundary.
发表机构
- College of Computer Science, Jiangsu University of Science and Technology（江苏科技大学计算机学院）
机构由 AI 辅助整理，请以论文原文为准。
