When Semantics Saturate or Emerge: Adaptation-Conditional Semantic Utility in Source-Free Cross-Domain Few-Shot Learning

arXiv:2608.06673v1 Announce Type: new Abstract: 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 eltazero and eltalora denote the Detailed-minus-Base accuracy before and after adaptation, respectively. Two recurring regimes emerge. In semantic saturation, eltazero>0 but 00: 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.

Related

• Improving CLIP Adaptation by Breaking Tail Alignment for Source-Free Cross-Domain Few-Shot Learning
• Training-free Cross-domain Few-shot Segmentation via Robust Semantic Representation and Matching
• DiffuSAM: Diffusion-Based Prompt-Free SAM2 for Few-Shot and Source-Free Medical Image Segmentation

Source: arXiv cs.CV | 2026-08-10