Metraipolis › archive › dc_ebe2f2ac006f

Generalizing Multimodal Foundational Models in Context-Driven Class Incremental Learning — arXiv:2610.27298

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.27298
License (as archived): CC0-1.0
Archived: 2026-10-21T07:07:38.184Z
SHA-256 of the archived text: 8da6a552b77eadf4b45207574e7a3aea926d7cb1eff8f4f55cde2cfa23f3fcbd
Stable URL of this page: https://metraipolis.com/documento/dc_ebe2f2ac006f

How to cite

Generalizing Multimodal Foundational Models in Context-Driven Class Incremental Learning — arXiv:2610.27298 — arXiv (en), https://arxiv.org/abs/2610.27298 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ebe2f2ac006f (Metraipolis archive dc_ebe2f2ac006f, sha256 8da6a552b77eadf4b45207574e7a3aea926d7cb1eff8f4f55cde2cfa23f3fcbd)

BibTeX

@misc{dcebe2f2ac006f,
  title = {Generalizing Multimodal Foundational Models in Context-Driven Class Incremental Learning — arXiv:2610.27298},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.27298},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ebe2f2ac006f; sha256 8da6a552b77eadf4b45207574e7a3aea926d7cb1eff8f4f55cde2cfa23f3fcbd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.27298. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Class-Incremental Learning (CIL) aims to learn new classes continuously without forgetting the previously learned ones. Recent works in CIL have significantly advanced across various modalities; however, at the intersection of audio-visual modality, this problem remains underexplored. While representations from multimodal foundational models (MFMs) encapsulate rich static priors, our preliminary analysis shows that these representations struggle in incremental settings. Motivated by this, we propose a framework that generalizes frozen MFMs to audio-visual CIL. Specifically, we leverage their dense audio and visual representations and employ an attention-based contextual guidance module, in which the audio representations serve as task-stable contextual guidance for the visual representations, enabling effective class recognition in the incremental setting. To further mitigate catastrophic forgetting and preserve stability across tasks, we employ feature- and logit-level distillation, which are primarily responsible for the reduced forgetting. Extensive evaluations across various audio-visual CIL benchmarks demonstrate that our approach consistently outperforms state-of-the-art methods. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.27298 — 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 2026-10-21T07:05:43.547Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).