The reviewed record of science sign in
Pith

arxiv: 2206.06487 · v3 · pith:WIUWXGUT · submitted 2022-06-13 · cs.CV · cs.LG

The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation

Reviewed by Pithpith:WIUWXGUTopen to challenge →

classification cs.CV cs.LG
keywords crossmodalknowledgemodalitydistillationhypothesistransferfocusinglearning
0
0 comments X
read the original abstract

Crossmodal knowledge distillation (KD) extends traditional knowledge distillation to the area of multimodal learning and demonstrates great success in various applications. To achieve knowledge transfer across modalities, a pretrained network from one modality is adopted as the teacher to provide supervision signals to a student network learning from another modality. In contrast to the empirical success reported in prior works, the working mechanism of crossmodal KD remains a mystery. In this paper, we present a thorough understanding of crossmodal KD. We begin with two case studies and demonstrate that KD is not a universal cure in crossmodal knowledge transfer. We then present the modality Venn diagram to understand modality relationships and the modality focusing hypothesis revealing the decisive factor in the efficacy of crossmodal KD. Experimental results on 6 multimodal datasets help justify our hypothesis, diagnose failure cases, and point directions to improve crossmodal knowledge transfer in the future.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Large Language Model Teaches Visual Students: Cross-Modality Transfer of Fine-Grained Conceptual Knowledge

    cs.CV 2026-06 unverdicted novelty 7.0

    LaViD distills LLM conceptual knowledge to vision models via LLM-generated MCQ soft labels, outperforming vision-language distillation baselines on fine-grained benchmarks while improving robustness on spurious correl...

  2. Purify-then-Align: Towards Robust Human Sensing under Modality Missing with Knowledge Distillation from Noisy Multimodal Teacher

    cs.CV 2026-04 unverdicted novelty 6.0

    PTA framework purifies noisy multimodal data via meta-learning and distills cross-modal knowledge through diffusion to create robust single-modality models under missing modalities.