# The Role of Masking for Efficient Supervised Knowledge Distillation of Vision Transformers

arXiv: https://arxiv.org/abs/2302.10494 · HTML: https://mlsanity.com/paper/2302.10494/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 41 of its 62 references that are in the map.
- First posted on arXiv 21 Feb 2023.

## Placed in

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

## Builds on (most cited first, 30 of 41)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [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)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [Segmenter: Transformer for Semantic Segmentation](https://mlsanity.com/paper/2105.05633/) (2021)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [Masked Feature Prediction for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2112.09133/) (2021)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers](https://mlsanity.com/paper/2106.10270/) (2021)
- [Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations](https://mlsanity.com/paper/2202.07800/) (2022)
- [AdaViT: Adaptive Tokens for Efficient Vision Transformer](https://mlsanity.com/paper/2112.07658/) (2021)
- [Masked Siamese Networks for Label-Efficient Learning](https://mlsanity.com/paper/2204.07141/) (2022)
- [Knowledge distillation: A good teacher is patient and consistent](https://mlsanity.com/paper/2106.05237/) (2021)
- [AdaViT: Adaptive Vision Transformers for Efficient Image Recognition](https://mlsanity.com/paper/2111.15668/) (2021)
- [Surgical Fine-Tuning Improves Adaptation to Distribution Shifts](https://mlsanity.com/paper/2210.11466/) (2022)
- [You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection](https://mlsanity.com/paper/2106.00666/) (2021)
- [Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels](https://mlsanity.com/paper/2101.05022/) (2021)
- [Curriculum Temperature for Knowledge Distillation](https://mlsanity.com/paper/2211.16231/) (2022)

## Built on by (most cited first, 8 of 8)

- [Ranked Entropy Minimization for Continual Test-Time Adaptation](https://mlsanity.com/paper/2505.16441/) (2025)
- [CM-MaskSD: Cross-Modality Masked Self-Distillation for Referring Image Segmentation](https://mlsanity.com/paper/2305.11481/) (2023)
- [Vision Transformer-based Semantic Communications With Importance-Aware Quantization](https://mlsanity.com/paper/2412.06038/) (2024)
- [Distillation Dynamics: Towards Understanding Feature-Based Distillation in Vision Transformers](https://mlsanity.com/paper/2511.06848/) (2025)
- [ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs](https://mlsanity.com/paper/2507.21420/) (2025)
- [CoMAD: A Multiple-Teacher Self-Supervised Distillation Framework](https://mlsanity.com/paper/2508.04816/) (2025)
- [Dynamic Pattern Alignment Learning for Pretraining Lightweight Human-Centric Vision Models](https://mlsanity.com/paper/2508.07144/) (2025)
- [FTerViT: Fully Ternary Vision Transformer](https://mlsanity.com/paper/2605.21171/) (2026)

## Abstract (arXiv)

Knowledge distillation is an effective method for training lightweight vision models. However, acquiring teacher supervision for training samples is often costly, especially from large-scale models like vision transformers (ViTs). In this paper, we develop a simple framework to reduce the supervision cost of ViT distillation: masking out a fraction of input tokens given to the teacher. By masking input tokens, one can skip the computations associated with the masked tokens without requiring any change to teacher parameters or architecture. We find that masking patches with the lowest student attention scores is highly effective, saving up to 50% of teacher FLOPs without any drop in student accuracy, while other masking criterion leads to suboptimal efficiency gains. Through in-depth analyses, we reveal that the student-guided masking provides a good curriculum to the student, making teacher supervision easier to follow during the early stage and challenging in the later stage.