# Cumulative Spatial Knowledge Distillation for Vision Transformers

Source: [Cumulative Spatial Knowledge Distillation for Vision Transformers](<https://www.sota2.com/research/paper/68fa70071e209131cea48add>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:59.941Z

Authors: Borui Zhao, Renjie Song, Jiajun Liang

Published: 2023-07-17T14:03:45.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2307.08500>)

[PDF](<https://arxiv.org/pdf/2307.08500.pdf>)
