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.
10 Julio Silva-Rodriguez, Hadi Chakor, Riadh Kobbi, Jose Dolz, and Ismail Ben Ayed
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
baseline 1
method 1
citation-polarity summary
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
BioVLM achieves state-of-the-art cross-modality generalization on biomedical VLMs by learning a prompt bank and routing inputs to the most discriminative prompts via low-entropy selection plus LLM distillation.
MG-MTTA improves VLM accuracy under modality-specific shifts by replacing pure entropy minimization with majorization-guided adaptation that incorporates a reliability-aware gate prior.
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.
-
BioVLM: Routing Prompts, Not Parameters, for Cross-Modality Generalization in Biomedical VLMs
BioVLM achieves state-of-the-art cross-modality generalization on biomedical VLMs by learning a prompt bank and routing inputs to the most discriminative prompts via low-entropy selection plus LLM distillation.
-
Majorization-Guided Test-Time Adaptation for Vision-Language Models under Modality-Specific Shift
MG-MTTA improves VLM accuracy under modality-specific shifts by replacing pure entropy minimization with majorization-guided adaptation that incorporates a reliability-aware gate prior.