# Non-target Divergence Hypothesis: Toward Understanding Domain Gaps in Cross-Modal Knowledge Distillation

arXiv: https://arxiv.org/abs/2409.02438 · HTML: https://mlsanity.com/paper/2409.02438/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal distillation, one of 12 directions in Knowledge distillation.
- Builds on 27 of its 57 references that are in the map.
- First posted on arXiv 4 Sep 2024.

## Placed in

- Knowledge distillation / [Multimodal distillation](https://mlsanity.com/distill/multimodal-distillation/)

## Builds on (most cited first, 27 of 27)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [Decoupled Knowledge Distillation](https://mlsanity.com/paper/2203.08679/) (2022)
- [On the Efficacy of Knowledge Distillation](https://mlsanity.com/paper/1910.01348/) (2019)
- [Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks](https://mlsanity.com/paper/2004.05937/) (2020)
- [Towards Understanding Knowledge Distillation](https://mlsanity.com/paper/2105.13093/) (2021)
- [2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds](https://mlsanity.com/paper/2207.04397/) (2022)
- [Anisotropic Convolutional Networks for 3D Semantic Scene Completion](https://mlsanity.com/paper/2004.02122/) (2020)
- [Understanding and Improving Knowledge Distillation](https://mlsanity.com/paper/2002.03532/) (2020)
- [Decoupled Multimodal Distilling for Emotion Recognition](https://mlsanity.com/paper/2303.13802/) (2023)
- [BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2211.09386/) (2022)
- [EPMF: Efficient Perception-aware Multi-sensor Fusion for 3D Semantic Segmentation](https://mlsanity.com/paper/2106.15277/) (2021)
- [Learnable Cross-modal Knowledge Distillation for Multi-modal Learning with Missing Modality](https://mlsanity.com/paper/2310.01035/) (2023)
- [The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation](https://mlsanity.com/paper/2206.06487/) (2022)
- [Co-advise: Cross Inductive Bias Distillation](https://mlsanity.com/paper/2106.12378/) (2021)
- [Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detection](https://mlsanity.com/paper/2108.03619/) (2021)
- [Feature Importance Ranking for Deep Learning](https://mlsanity.com/paper/2010.08973/) (2020)
- [XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning](https://mlsanity.com/paper/2211.13929/) (2022)
- [Decomposed Cross-modal Distillation for RGB-based Temporal Action Detection](https://mlsanity.com/paper/2303.17285/) (2023)
- [Enhanced Multimodal Representation Learning with Cross-modal KD](https://mlsanity.com/paper/2306.07646/) (2023)
- [Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation Learning](https://mlsanity.com/paper/2405.20606/) (2024)
- [LabelDistill: Label-guided Cross-modal Knowledge Distillation for Camera-based 3D Object Detection](https://mlsanity.com/paper/2407.10164/) (2024)

## Built on by (most cited first, 1 of 1)

- [Information-Theoretic Criteria for Knowledge Distillation in Multimodal Learning](https://mlsanity.com/paper/2510.13182/) (2025)

## Abstract (arXiv)

Compared to single-modal knowledge distillation, cross-modal knowledge distillation faces more severe challenges due to domain gaps between modalities. Although various methods have proposed various solutions to overcome these challenges, there is still limited research on how domain gaps affect cross-modal knowledge distillation. This paper provides an in-depth analysis and evaluation of this issue. We first introduce the Non-Target Divergence Hypothesis (NTDH) to reveal the impact of domain gaps on cross-modal knowledge distillation. Our key finding is that domain gaps between modalities lead to distribution differences in non-target classes, and the smaller these differences, the better the performance of cross-modal knowledge distillation. Subsequently, based on Vapnik-Chervonenkis (VC) theory, we derive the upper and lower bounds of the approximation error for cross-modal knowledge distillation, thereby theoretically validating the NTDH. Finally, experiments on five cross-modal datasets further confirm the validity, generalisability, and applicability of the NTDH.