# Fuse Before Transfer: Knowledge Fusion for Heterogeneous Distillation

arXiv: https://arxiv.org/abs/2410.12342 · HTML: https://mlsanity.com/paper/2410.12342/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 36 of its 42 references that are in the map.
- First posted on arXiv 16 Oct 2024.

## Placed in

- Knowledge distillation / [General knowledge distillation methods](https://mlsanity.com/distill/general-knowledge-distillation-methods/)

## Builds on (most cited first, 30 of 36)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [CoAtNet: Marrying Convolution and Attention for All Data Sizes](https://mlsanity.com/paper/2106.04803/) (2021)
- [Decoupled Knowledge Distillation](https://mlsanity.com/paper/2203.08679/) (2022)
- [A Comprehensive Overhaul of Feature Distillation](https://mlsanity.com/paper/1904.01866/) (2019)
- [ResMLP: Feedforward networks for image classification with data-efficient training](https://mlsanity.com/paper/2105.03404/) (2021)
- [How Do Vision Transformers Work?](https://mlsanity.com/paper/2202.06709/) (2022)
- [Distilling Knowledge via Knowledge Review](https://mlsanity.com/paper/2104.09044/) (2021)
- [Correlation Congruence for Knowledge Distillation](https://mlsanity.com/paper/1904.01802/) (2019)
- [Knowledge Distillation from A Stronger Teacher](https://mlsanity.com/paper/2205.10536/) (2022)
- [UniFormer: Unifying Convolution and Self-attention for Visual Recognition](https://mlsanity.com/paper/2201.09450/) (2022)
- [Patches Are All You Need?](https://mlsanity.com/paper/2201.09792/) (2022)
- [Knowledge Distillation with the Reused Teacher Classifier](https://mlsanity.com/paper/2203.14001/) (2022)
- [Logit Standardization in Knowledge Distillation](https://mlsanity.com/paper/2403.01427/) (2024)
- [One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation](https://mlsanity.com/paper/2310.19444/) (2023)
- [Adaptive Multi-Teacher Multi-level Knowledge Distillation](https://mlsanity.com/paper/2103.04062/) (2021)
- [Cross-Architecture Knowledge Distillation](https://mlsanity.com/paper/2207.05273/) (2022)
- [Co-advise: Cross Inductive Bias Distillation](https://mlsanity.com/paper/2106.12378/) (2021)

## Built on by (most cited first, 4 of 4)

- [UHKD: A Unified Framework for Heterogeneous Knowledge Distillation via Frequency-Domain Representations](https://mlsanity.com/paper/2510.24116/) (2025)
- [SFKD: Spatial--Frequency Joint-Aware Heterogeneous Knowledge Distillation via Multi-Level Wavelet Spectral Interaction](https://mlsanity.com/paper/2607.01906/) (2026)
- [CoCaRS: Correlation Calibration-Based Redundancy Suppression for Heterogeneous Knowledge Distillation](https://mlsanity.com/paper/2607.27054/) (2026)
- [GRAFT: Growing Agglomerative Foundation Models via Continual Teacher Distillation](https://mlsanity.com/paper/2610.02597/) (2026)

## Abstract (arXiv)

Most knowledge distillation (KD) methodologies predominantly focus on teacher-student pairs with similar architectures, such as both being convolutional neural networks (CNNs). However, the potential and flexibility of KD can be greatly improved by expanding it to novel Cross-Architecture KD (CAKD), where the knowledge of homogeneous and heterogeneous teachers can be transferred flexibly to a given student. The primary challenge in CAKD lies in the substantial feature gaps between heterogeneous models, originating from the distinction of their inherent inductive biases and module functions. To this end, we introduce an assistant model as a bridge to facilitate smooth feature knowledge transfer between heterogeneous teachers and students. More importantly, within our proposed design principle, the assistant model combines the advantages of cross-architecture inductive biases and module functions by merging convolution and attention modules derived from both student and teacher module functions. Furthermore, we observe that heterogeneous features exhibit diverse spatial distributions in CAKD, hindering the effectiveness of conventional pixel-wise mean squared error (MSE) loss. Therefore, we leverage a spatial-agnostic InfoNCE loss to align features after spatial smoothing, thereby improving the feature alignments in CAKD. Our proposed method is evaluated across some homogeneous model pairs and arbitrary heterogeneous combinations of CNNs, ViTs, and MLPs, achieving state-of-the-art performance for distilled models with a maximum gain of 11.47% on CIFAR-100 and 3.67% on ImageNet-1K. Our code and models will be released.