# DisCoM-KD: Cross-Modal Knowledge Distillation via Disentanglement Representation and Adversarial Learning arXiv: https://arxiv.org/abs/2408.07080 ยท HTML: https://mlsanity.com/paper/2408.07080/ ## Key facts - Cited by 6 papers in the map (data through 14 Oct 2026). - Placed in Multimodal distillation, one of 12 directions in Knowledge distillation. - Builds on 22 of its 32 references that are in the map. - First posted on arXiv 5 Aug 2024. ## Placed in - Knowledge distillation / [Multimodal distillation](https://mlsanity.com/distill/multimodal-distillation/) ## Builds on (most cited first, 22 of 22) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015) - [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015) - [Decoupled Knowledge Distillation](https://mlsanity.com/paper/2203.08679/) (2022) - [Knowledge Distillation from A Stronger Teacher](https://mlsanity.com/paper/2205.10536/) (2022) - [Learning Factorized Multimodal Representations](https://mlsanity.com/paper/1806.06176/) (2018) - [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022) - [Curriculum Temperature for Knowledge Distillation](https://mlsanity.com/paper/2211.16231/) (2022) - [Logit Standardization in Knowledge Distillation](https://mlsanity.com/paper/2403.01427/) (2024) - [Class Attention Transfer Based Knowledge Distillation](https://mlsanity.com/paper/2304.12777/) (2023) - [Disentangling visual and written concepts in CLIP](https://mlsanity.com/paper/2206.07835/) (2022) - [Feature Guided Masked Autoencoder for Self-supervised Learning in Remote Sensing](https://mlsanity.com/paper/2310.18653/) (2023) - [The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation](https://mlsanity.com/paper/2206.06487/) (2022) - [DISSECT: Disentangled Simultaneous Explanations via Concept Traversals](https://mlsanity.com/paper/2105.15164/) (2021) - [Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model](https://mlsanity.com/paper/2111.13333/) (2021) - [XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning](https://mlsanity.com/paper/2211.13929/) (2022) - [A Review on Methods and Applications in Multimodal Deep Learning](https://mlsanity.com/paper/2202.09195/) (2022) - [Towards Counterfactual Image Manipulation via CLIP](https://mlsanity.com/paper/2207.02812/) (2022) - [Cross-Modal Distillation for RGB-Depth Person Re-Identification](https://mlsanity.com/paper/1810.11641/) (2018) - [POEM: Polarization of Embeddings for Domain-Invariant Representations](https://mlsanity.com/paper/2305.13046/) (2023) - [DistilVPR: Cross-Modal Knowledge Distillation for Visual Place Recognition](https://mlsanity.com/paper/2312.10616/) (2023) - [Multi-Modal RGB-D Scene Recognition Across Domains](https://mlsanity.com/paper/2103.14672/) (2021) ## Built on by (most cited first, 6 of 6) - [Applications of Knowledge Distillation in Remote Sensing: A Survey](https://mlsanity.com/paper/2409.12111/) (2024) - [Revisiting Cross-Modal Knowledge Distillation: A Disentanglement Approach for RGBD Semantic Segmentation](https://mlsanity.com/paper/2505.24361/) (2025) - [Multi-modal Co-learning for Earth Observation: Enhancing single-modality models via modality collaboration](https://mlsanity.com/paper/2510.19579/) (2025) - [On What Depends the Robustness of Multi-source Models to Missing Data in Earth Observation?](https://mlsanity.com/paper/2503.19719/) (2025) - [Can multimodal representation learning by alignment preserve modality-specific information?](https://mlsanity.com/paper/2509.17943/) (2025) - [Co-Learning for Missing Arbitrary Modalities in Multi-modal Classification](https://mlsanity.com/paper/2607.24683/) (2026) ## Abstract (arXiv) Cross-modal knowledge distillation (CMKD) refers to the scenario in which a learning framework must handle training and test data that exhibit a modality mismatch, more precisely, training and test data do not cover the same set of data modalities. Traditional approaches for CMKD are based on a teacher/student paradigm where a teacher is trained on multi-modal data with the aim to successively distill knowledge from a multi-modal teacher to a single-modal student. Despite the widespread adoption of such paradigm, recent research has highlighted its inherent limitations in the context of cross-modal knowledge transfer.Taking a step beyond the teacher/student paradigm, here we introduce a new framework for cross-modal knowledge distillation, named DisCoM-KD (Disentanglement-learning based Cross-Modal Knowledge Distillation), that explicitly models different types of per-modality information with the aim to transfer knowledge from multi-modal data to a single-modal classifier. To this end, DisCoM-KD effectively combines disentanglement representation learning with adversarial domain adaptation to simultaneously extract, foreach modality, domain-invariant, domain-informative and domain-irrelevant features according to a specific downstream task. Unlike the traditional teacher/student paradigm, our framework simultaneously learns all single-modal classifiers, eliminating the need to learn each student model separately as well as the teacher classifier. We evaluated DisCoM-KD on three standard multi-modal benchmarks and compared its behaviourwith recent SOTA knowledge distillation frameworks. The findings clearly demonstrate the effectiveness of DisCoM-KD over competitors considering mismatch scenarios involving both overlapping and non-overlapping modalities. These results offer insights to reconsider the traditional paradigm for distilling information from multi-modal data to single-modal neural networks.