Codebook-Guided Cross-Modal Knowledge Distillation for Structurally Heterogeneous Features

תקציר מקורי באנגליתarXiv:2609.37243v2 Announce Type: replace-cross Abstract: 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 featu