# Masked Generative Distillation

arXiv: https://arxiv.org/abs/2205.01529 · HTML: https://mlsanity.com/paper/2205.01529/

## Key facts

- Cited by 107 papers in the map (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 33 of its 39 references that are in the map.
- First posted on arXiv 3 May 2022.

## Placed in

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

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [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)
- [Res2Net: A New Multi-scale Backbone Architecture](https://mlsanity.com/paper/1904.01169/) (2019)
- [On the Efficacy of Knowledge Distillation](https://mlsanity.com/paper/1910.01348/) (2019)
- [A Comprehensive Overhaul of Feature Distillation](https://mlsanity.com/paper/1904.01866/) (2019)
- [SOLO: Segmenting Objects by Locations](https://mlsanity.com/paper/1912.04488/) (2019)
- [Distilling Knowledge via Knowledge Review](https://mlsanity.com/paper/2104.09044/) (2021)
- [Structured Knowledge Distillation for Dense Prediction](https://mlsanity.com/paper/1903.04197/) (2019)
- [RepPoints: Point Set Representation for Object Detection](https://mlsanity.com/paper/1904.11490/) (2019)
- [Distilling Object Detectors with Fine-grained Feature Imitation](https://mlsanity.com/paper/1906.03609/) (2019)
- [Channel-wise Knowledge Distillation for Dense Prediction](https://mlsanity.com/paper/2011.13256/) (2020)
- [Focal and Global Knowledge Distillation for Detectors](https://mlsanity.com/paper/2111.11837/) (2021)
- [Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective](https://mlsanity.com/paper/2102.00650/) (2021)
- [General Instance Distillation for Object Detection](https://mlsanity.com/paper/2103.02340/) (2021)
- [Distilling Object Detectors via Decoupled Features](https://mlsanity.com/paper/2103.14475/) (2021)

## Built on by (most cited first, 30 of 107)

- [Effective Whole-body Pose Estimation with Two-stages Distillation](https://mlsanity.com/paper/2307.15880/) (2023)
- [From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels](https://mlsanity.com/paper/2303.13005/) (2023)
- [BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2211.09386/) (2022)
- [Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2303.05892/) (2023)
- [UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers](https://mlsanity.com/paper/2301.13741/) (2023)
- [NORM: Knowledge Distillation via N-to-One Representation Matching](https://mlsanity.com/paper/2305.13803/) (2023)
- [CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers](https://mlsanity.com/paper/2305.17455/) (2023)
- [Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillation](https://mlsanity.com/paper/2404.11958/) (2024)
- [Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation](https://mlsanity.com/paper/2206.06067/) (2022)
- [DAMO-YOLO : A Report on Real-Time Object Detection Design](https://mlsanity.com/paper/2211.15444/) (2022)
- [DETRDistill: A Universal Knowledge Distillation Framework for DETR-families](https://mlsanity.com/paper/2211.10156/) (2022)
- [ViTKD: Practical Guidelines for ViT feature knowledge distillation](https://mlsanity.com/paper/2209.02432/) (2022)
- [Masked Image Modeling: A Survey](https://mlsanity.com/paper/2408.06687/) (2024)
- [FreeKD: Knowledge Distillation via Semantic Frequency Prompt](https://mlsanity.com/paper/2311.12079/) (2023)
- [Exploring Inconsistent Knowledge Distillation for Object Detection with Data Augmentation](https://mlsanity.com/paper/2209.09841/) (2022)
- [Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge Distillation](https://mlsanity.com/paper/2412.08139/) (2024)
- [LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillation](https://mlsanity.com/paper/2304.11379/) (2023)
- [ACAM-KD: Adaptive and Cooperative Attention Masking for Knowledge Distillation](https://mlsanity.com/paper/2503.06307/) (2025)
- [D3ETR: Decoder Distillation for Detection Transformer](https://mlsanity.com/paper/2211.09768/) (2022)
- [Rethinking Centered Kernel Alignment in Knowledge Distillation](https://mlsanity.com/paper/2401.11824/) (2024)
- [CM-MaskSD: Cross-Modality Masked Self-Distillation for Referring Image Segmentation](https://mlsanity.com/paper/2305.11481/) (2023)
- [BPKD: Boundary Privileged Knowledge Distillation For Semantic Segmentation](https://mlsanity.com/paper/2306.08075/) (2023)
- [AMFD: Distillation via Adaptive Multimodal Fusion for Multispectral Pedestrian Detection](https://mlsanity.com/paper/2405.12944/) (2024)
- [KD-DETR: Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling](https://mlsanity.com/paper/2211.08071/) (2022)
- [NormKD: Normalized Logits for Knowledge Distillation](https://mlsanity.com/paper/2308.00520/) (2023)
- [Student-friendly Knowledge Distillation](https://mlsanity.com/paper/2305.10893/) (2023)
- [VanillaKD: Revisit the Power of Vanilla Knowledge Distillation from Small Scale to Large Scale](https://mlsanity.com/paper/2305.15781/) (2023)
- [Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation](https://mlsanity.com/paper/2402.17316/) (2024)
- [MedDet: Generative Adversarial Distillation for Efficient Cervical Disc Herniation Detection](https://mlsanity.com/paper/2409.00204/) (2024)
- [ScaleKD: Strong Vision Transformers Could Be Excellent Teachers](https://mlsanity.com/paper/2411.06786/) (2024)

## Abstract (arXiv)

Knowledge distillation has been applied to various tasks successfully. The current distillation algorithm usually improves students' performance by imitating the output of the teacher. This paper shows that teachers can also improve students' representation power by guiding students' feature recovery. From this point of view, we propose Masked Generative Distillation (MGD), which is simple: we mask random pixels of the student's feature and force it to generate the teacher's full feature through a simple block. MGD is a truly general feature-based distillation method, which can be utilized on various tasks, including image classification, object detection, semantic segmentation and instance segmentation. We experiment on different models with extensive datasets and the results show that all the students achieve excellent improvements. Notably, we boost ResNet-18 from 69.90% to 71.69% ImageNet top-1 accuracy, RetinaNet with ResNet-50 backbone from 37.4 to 41.0 Boundingbox mAP, SOLO based on ResNet-50 from 33.1 to 36.2 Mask mAP and DeepLabV3 based on ResNet-18 from 73.20 to 76.02 mIoU. Our codes are available at https://github.com/yzd-v/MGD.