# Cumulative Spatial Knowledge Distillation for Vision Transformers

arXiv: https://arxiv.org/abs/2307.08500 · HTML: https://mlsanity.com/paper/2307.08500/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 39 of its 47 references that are in the map.
- First posted on arXiv 17 Jul 2023.

## Placed in

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

## Builds on (most cited first, 30 of 39)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [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)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [Decoupled Knowledge Distillation](https://mlsanity.com/paper/2203.08679/) (2022)

## Built on by (most cited first, 18 of 18)

- [A Survey on Transformer Compression](https://mlsanity.com/paper/2402.05964/) (2024)
- [AMD: Automatic Multi-step Distillation of Large-scale Vision Models](https://mlsanity.com/paper/2407.04208/) (2024)
- [ScaleKD: Strong Vision Transformers Could Be Excellent Teachers](https://mlsanity.com/paper/2411.06786/) (2024)
- [Weight Copy and Low-Rank Adaptation for Few-Shot Distillation of Vision Transformers](https://mlsanity.com/paper/2404.09326/) (2024)
- [Fuse Before Transfer: Knowledge Fusion for Heterogeneous Distillation](https://mlsanity.com/paper/2410.12342/) (2024)
- [Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding](https://mlsanity.com/paper/2604.19609/) (2026)
- [HDKD: Hybrid Data-Efficient Knowledge Distillation Network for Medical Image Classification](https://mlsanity.com/paper/2407.07516/) (2024)
- [Dual-modal Prior Semantic Guided Infrared and Visible Image Fusion for Intelligent Transportation System](https://mlsanity.com/paper/2403.16227/) (2024)
- [Delving Deep into Semantic Relation Distillation](https://mlsanity.com/paper/2503.21269/) (2025)
- [Image Recognition with Online Lightweight Vision Transformer: A Survey](https://mlsanity.com/paper/2505.03113/) (2025)
- [CTRL-F: Pairing Convolution with Transformer for Image Classification via Multi-Level Feature Cross-Attention and Representation Learning Fusion](https://mlsanity.com/paper/2407.06673/) (2024)
- [Mitigating Spurious Correlations in Weakly Supervised Semantic Segmentation via Cross-architecture Consistency Regularization](https://mlsanity.com/paper/2507.21959/) (2025)
- [UHKD: A Unified Framework for Heterogeneous Knowledge Distillation via Frequency-Domain Representations](https://mlsanity.com/paper/2510.24116/) (2025)
- [TOLiD: Bridging the Architecture Gap in Vision Foundation Model to LiDAR Pretraining via Token Lifting for Distillation](https://mlsanity.com/paper/2607.10762/) (2026)
- [Compact Vision Transformer by Reduction of Kernel Complexity](https://mlsanity.com/paper/2507.12780/) (2025)
- [Heterogeneous Complementary Distillation](https://mlsanity.com/paper/2511.10942/) (2025)
- [Weak-to-Strong Knowledge Distillation Accelerates Visual Learning](https://mlsanity.com/paper/2604.15451/) (2026)
- [CoCaRS: Correlation Calibration-Based Redundancy Suppression for Heterogeneous Knowledge Distillation](https://mlsanity.com/paper/2607.27054/) (2026)

## Abstract (arXiv)

Distilling knowledge from convolutional neural networks (CNNs) is a double-edged sword for vision transformers (ViTs). It boosts the performance since the image-friendly local-inductive bias of CNN helps ViT learn faster and better, but leading to two problems: (1) Network designs of CNN and ViT are completely different, which leads to different semantic levels of intermediate features, making spatial-wise knowledge transfer methods (e.g., feature mimicking) inefficient. (2) Distilling knowledge from CNN limits the network convergence in the later training period since ViT's capability of integrating global information is suppressed by CNN's local-inductive-bias supervision. To this end, we present Cumulative Spatial Knowledge Distillation (CSKD). CSKD distills spatial-wise knowledge to all patch tokens of ViT from the corresponding spatial responses of CNN, without introducing intermediate features. Furthermore, CSKD exploits a Cumulative Knowledge Fusion (CKF) module, which introduces the global response of CNN and increasingly emphasizes its importance during the training. Applying CKF leverages CNN's local inductive bias in the early training period and gives full play to ViT's global capability in the later one. Extensive experiments and analysis on ImageNet-1k and downstream datasets demonstrate the superiority of our CSKD. Code will be publicly available.