Metraipolis › archive › dc_985c20fdc878
Dual-Stream Semantic Guidance with Prototype Anchor Calibration for Source-Fully-Free Adaptation of Vision-Language Models — arXiv:2608.28145
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28145
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T11:33:10.707Z
- SHA-256 of the archived text
309bf7642d5e80cb7c9c1a6d94ff7c7fd83b6e098013a70500c05b13e3eb194a- Stable URL of this page
https://metraipolis.com/documento/dc_985c20fdc878
How to cite
Dual-Stream Semantic Guidance with Prototype Anchor Calibration for Source-Fully-Free Adaptation of Vision-Language Models — arXiv:2608.28145 — arXiv (en), https://arxiv.org/abs/2608.28145 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_985c20fdc878 (Metraipolis archive dc_985c20fdc878, sha256 309bf7642d5e80cb7c9c1a6d94ff7c7fd83b6e098013a70500c05b13e3eb194a)
BibTeX
@misc{dc985c20fdc878,
title = {Dual-Stream Semantic Guidance with Prototype Anchor Calibration for Source-Fully-Free Adaptation of Vision-Language Models — arXiv:2608.28145},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28145},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_985c20fdc878; sha256 309bf7642d5e80cb7c9c1a6d94ff7c7fd83b6e098013a70500c05b13e3eb194a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28145. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Source-Fully-Free Domain Adaptation (SFF-DA) has emerged as a strategic paradigm to adapt Vision-Language Models (VLMs) without any access to source data or task-specific source models. However, we identify a critical Dual Semantic Drift that hinders this process: static drift arising from the rigidity of fixed class embeddings, and dynamic drift stemming from the divergence of generated captions, causing severe semantic misalignment that intensifies the stability-plasticity dilemma. To address this, we propose DSSG (Dual-Stream Semantic Guidance), an end-to-end framework that reconciles fine-grained plasticity with global stability. Our core contribution is the Dual Semantic Guidance (DSG) module, which integrates a caption stream for domain-specific knowledge with a class-anchor stream to anchor global categorical consistency. Furthermore, a Dynamic Cross-Modal Knowledge Distillation (CMKD) module is introduced to leverage the evolving teacher distribution for calibrating teacher-student consistency. Building upon DSSG, we further introduce Prototype Anchor Calibration (PAC), yielding DSSG-PAC, which periodically calibrates prototype anchors and caches them until the next calibration. This design reduces redundant text-side computation while preserving the adaptability of class guidance to the evolving text space. We further establish SFF-DA risk bounds that relate student risk to semantic-teacher quality and teacher--student discrepancy. Extensive experiments demonstrate that DSSG consistently outperforms current state-of-the-art methods across multiple benchmarks, while DSSG-PAC largely preserves its adaptation performance with 18.9% lower total adaptation time. The code is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-31 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.28145 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T11:10:05.307Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).