The paper introduces the VODA setting for domain adaptation from scratch using vision-language models and presents TS-DRD, which achieves competitive performance on standard benchmarks without source models.
Title resolution pending
3 Pith papers cite this work, alongside 20 external citations. Polarity classification is still indexing.
3
Pith papers citing it
20
external citations · external index
citation-role summary
baseline 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
baseline 1polarities
baseline 1representative citing papers
FUSE creates full-spectrum unlearnable perturbations using random spectral masking during training and cross-band guidance to enforce consistency between frequency components.
S²PLR identifies a safe subspace for reliable pseudo-labels in source-free graph domain adaptation using semantic committee signals and structural contrastive verification, then applies noise-tolerant regularization to uncertain samples.
citing papers explorer
-
Rethinking the Need for Source Models: Source-Free Domain Adaptation from Scratch Guided by a Vision-Language Model
The paper introduces the VODA setting for domain adaptation from scratch using vision-language models and presents TS-DRD, which achieves competitive performance on standard benchmarks without source models.
-
Full spectrum Unlearnable Examples via Spectral Equalization
FUSE creates full-spectrum unlearnable perturbations using random spectral masking during training and cross-band guidance to enforce consistency between frequency components.
-
Safe-Subspace Pseudo-Label Refinement for Source-Free Graph Domain Adaptation
S²PLR identifies a safe subspace for reliable pseudo-labels in source-free graph domain adaptation using semantic committee signals and structural contrastive verification, then applies noise-tolerant regularization to uncertain samples.