AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Reclaiming Lost Text Layers for Source-Free Cross-Domain Few-Shot Learning

Zhenyu Zhang, Guangyao Chen, Yixiong Zou, Yuhua Li, Ruixuan Li

CVPR 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain few-shot with transformers · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add VtT to CLIP-LoRA-VisionCLIP-LoRA-Vision · CDFSL 5-way 1-shot avgaccuracy: 55.97 -> 58.23Improved
add VtT to MapleMaple · CDFSL 5-way 1-shot avgaccuracy: 53.07 -> 55.15Improved
add VtT to SigLIP2-LoRA and PE-Core-LoRA backbonesSigLIP2-LoRA / PE-Core-LoRA · CDFSL 5-way 5-shot avgaccuracy: 65.96 -> 67.75; 68.64 -> 70.05Improved
emphasize the lost text layer instead of removing it (ablation)CLIP fine-tuning · CDFSL 5-way 1-shot avgaccuracy: 56.3 -> 56.7Improved
choose the wrong layer to remove (ablation)Removal strategy · CDFSL 5-way 1-shot avgaccuracy: 56.3 -> 50.7Hurt
add TIA module (ablation)CLIP-LoRA-Vision · CDFSL 5-way 1-shot avgaccuracy: 55.9 -> 56.9Improved
add V-T Fusion on top of TIA (ablation)VtT · CDFSL 5-way 1-shot avgaccuracy: 56.9 -> 57.6Improved
add DGSO on top of TIA + V-T Fusion (ablation)VtT · CDFSL 5-way 1-shot avgaccuracy: 57.6 -> 58.2Improved
use deep-to-shallow instead of shallow-to-deep scanning (ablation)V-T Fusion · CDFSL 5-way 1-shot avgaccuracy: 57.7 -> 58.2Improved
use bidirectional scanning instead of deep-to-shallow (ablation)V-T Fusion · CDFSL 5-way 1-shot avgaccuracy: 58.2 -> 58.2No clear effect
fuse both visual and text features rather than one modality (ablation)V-T Fusion · CDFSL 5-way 1-shot avgaccuracy: 57.1 / 57.5 -> 58.2Improved
use SSM fusion instead of mean averaging (ablation)V-T Fusion · CDFSL 5-way 1-shot avgaccuracy: 57.0 -> 58.2Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy