# UHKD: A Unified Framework for Heterogeneous Knowledge Distillation via Frequency-Domain Representations

arXiv: https://arxiv.org/abs/2510.24116 · HTML: https://mlsanity.com/paper/2510.24116/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 55 of its 67 references that are in the map.
- First posted on arXiv 28 Oct 2025.

## Placed in

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

## Builds on (most cited first, 30 of 55)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [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)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [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)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [Born Again Neural Networks](https://mlsanity.com/paper/1805.04770/) (2018)
- [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 Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons](https://mlsanity.com/paper/1811.03233/) (2018)
- [Knowledge Distillation from A Stronger Teacher](https://mlsanity.com/paper/2205.10536/) (2022)
- [Focal Frequency Loss for Image Reconstruction and Synthesis](https://mlsanity.com/paper/2012.12821/) (2020)
- [Learning in the Frequency Domain](https://mlsanity.com/paper/2002.12416/) (2020)

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

- [Preserving Knowledge across Space and Time for Continual Video Deepfake Detection](https://mlsanity.com/paper/2609.03446/) (2026)

## Abstract (arXiv)

Knowledge distillation (KD) is an effective model compression technique that transfers knowledge from a high-performance teacher to a lightweight student, reducing computational and storage costs while maintaining competitive accuracy. However, most existing KD methods are tailored for homogeneous models and perform poorly in heterogeneous settings, particularly when intermediate features are involved. Semantic discrepancies across architectures hinder effective use of intermediate representations from the teacher model, while prior heterogeneous KD studies mainly focus on the logits space, underutilizing rich semantic information in intermediate layers. To address this, Unified Heterogeneous Knowledge Distillation (UHKD) is proposed, a framework that leverages intermediate features in the frequency domain for cross-architecture transfer. Frequency-domain representations are leveraged to capture global semantic knowledge and mitigate representational discrepancies between heterogeneous teacher-student pairs. Specifically, a Feature Transformation Module (FTM) generates compact frequency-domain representations of teacher features, while a learnable Feature Alignment Module (FAM) projects student features and aligns them via multi-level matching. Training is guided by a joint objective combining mean squared error on intermediate features with Kullback-Leibler divergence on logits. Extensive experiments on CIFAR-100 and ImageNet-1K demonstrate the effectiveness of the proposed approach, achieving maximum gains of 5.59% and 0.83% over the latest heterogeneous distillation method on the two datasets, respectively. Code will be released soon.