Metraipolis › archive › dc_4f33da044cba

Codebook-Guided Cross-Modal Knowledge Distillation for Structurally Heterogeneous Features — arXiv:2609.37243

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.37243
License (as archived): CC0-1.0
Archived: 2026-10-07T16:27:04.129Z
SHA-256 of the archived text: 205142d1c26a458f0711233961dbf672e9396063ca5f236e831452b35e9bfdde
Stable URL of this page: https://metraipolis.com/documento/dc_4f33da044cba

How to cite

Codebook-Guided Cross-Modal Knowledge Distillation for Structurally Heterogeneous Features — arXiv:2609.37243 — arXiv (en), https://arxiv.org/abs/2609.37243 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4f33da044cba (Metraipolis archive dc_4f33da044cba, sha256 205142d1c26a458f0711233961dbf672e9396063ca5f236e831452b35e9bfdde)

BibTeX

@misc{dc4f33da044cba,
  title = {Codebook-Guided Cross-Modal Knowledge Distillation for Structurally Heterogeneous Features — arXiv:2609.37243},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37243},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4f33da044cba; sha256 205142d1c26a458f0711233961dbf672e9396063ca5f236e831452b35e9bfdde},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37243. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Cross-modal knowledge distillation transfers knowledge from a teacher modality to a student modality. Existing feature-level alignment methods typically assume that teacher and student features reside in structurally alignable representation spaces. However, this assumption does not hold when cross-modal features are structurally heterogeneous and lack clear unit-level correspondence, such as 2D spatial visual grids and 1D temporal audio sequences, thereby limiting the applicability of feature-level alignment. To address this challenge, we propose a cross-modal distillation framework that enables effective knowledge transfer across structurally heterogeneous feature spaces via a vector-quantized codebook. Specifically, teacher features are abstracted into a set of vector-form codes regardless of their original feature structure, and the selected codes serve as concept-level anchors for student learning. Code selection is guided by both task relevance and student compatibility, allowing the student to receive transferable teacher knowledge without requiring direct unit-level feature alignment. Experimental results across diverse cross-modal distillation scenarios demonstrate the effectiveness of the proposed framework on classification and semantic segmentation tasks.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.37243 — 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 2026-10-07T15:54:53.962Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).