# Hard Patches Mining for Masked Image Modeling

arXiv: https://arxiv.org/abs/2304.05919 · HTML: https://mlsanity.com/paper/2304.05919/

## Key facts

- Cited by 57 papers in the map (data through 14 Oct 2026).
- Builds on 71 of its 91 references that are in the map.
- First posted on arXiv 12 Apr 2023.

## Builds on (most cited first, 30 of 71)

- [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)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)

## Built on by (most cited first, 30 of 57)

- [Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness](https://mlsanity.com/paper/2504.01901/) (2025)
- [Reconstructive Visual Instruction Tuning](https://mlsanity.com/paper/2410.09575/) (2024)
- [Predicting Gradient is Better: Exploring Self-Supervised Learning for SAR ATR with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2311.15153/) (2023)
- [HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception](https://mlsanity.com/paper/2310.20695/) (2023)
- [The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer](https://mlsanity.com/paper/2504.10462/) (2025)
- [Continual Forgetting for Pre-trained Vision Models](https://mlsanity.com/paper/2403.11530/) (2024)
- [Masked Image Modeling: A Survey](https://mlsanity.com/paper/2408.06687/) (2024)
- [FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learning](https://mlsanity.com/paper/2412.12032/) (2024)
- [DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions](https://mlsanity.com/paper/2309.03576/) (2023)
- [MiM: Mask in Mask Self-Supervised Pre-Training for 3D Medical Image Analysis](https://mlsanity.com/paper/2404.15580/) (2024)
- [Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding](https://mlsanity.com/paper/2502.11168/) (2025)
- [EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation](https://mlsanity.com/paper/2504.09209/) (2025)
- [Masked Modeling for Self-supervised Representation Learning on Vision and Beyond](https://mlsanity.com/paper/2401.00897/) (2023)
- [Representing Part-Whole Hierarchies in Foundation Models by Learning Localizability, Composability, and Decomposability from Anatomy via Self-Supervision](https://mlsanity.com/paper/2404.15672/) (2024)
- [MIMIR: Masked Image Modeling for Mutual Information-based Adversarial Robustness](https://mlsanity.com/paper/2312.04960/) (2023)
- [Harnessing Massive Satellite Imagery with Efficient Masked Image Modeling](https://mlsanity.com/paper/2406.11933/) (2024)
- [AnatoMask: Enhancing Medical Image Segmentation with Reconstruction-guided Self-masking](https://mlsanity.com/paper/2407.06468/) (2024)
- [Using Unreliable Pseudo-Labels for Label-Efficient Semantic Segmentation](https://mlsanity.com/paper/2306.02314/) (2023)
- [ColorMAE: Exploring data-independent masking strategies in Masked AutoEncoders](https://mlsanity.com/paper/2407.13036/) (2024)
- [M-SpecGene: Generalized Foundation Model for RGBT Multispectral Vision](https://mlsanity.com/paper/2507.16318/) (2025)
- [Pulling Target to Source: A New Perspective on Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2305.13752/) (2023)
- [Free-ATM: Exploring Unsupervised Learning on Diffusion-Generated Images with Free Attention Masks](https://mlsanity.com/paper/2308.06739/) (2023)
- [Linguistics-aware Masked Image Modeling for Self-supervised Scene Text Recognition](https://mlsanity.com/paper/2503.18746/) (2025)
- [Masked Image Residual Learning for Scaling Deeper Vision Transformers](https://mlsanity.com/paper/2309.14136/) (2023)
- [Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder](https://mlsanity.com/paper/2310.16318/) (2023)
- [Bootstrap Masked Visual Modeling via Hard Patches Mining](https://mlsanity.com/paper/2312.13714/) (2023)
- [Morphing Tokens Draw Strong Masked Image Models](https://mlsanity.com/paper/2401.00254/) (2023)
- [An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-Training](https://mlsanity.com/paper/2404.12210/) (2024)
- [MMCLIP: Cross-modal Attention Masked Modelling for Medical Language-Image Pre-Training](https://mlsanity.com/paper/2407.19546/) (2024)
- [Learning with Unmasked Tokens Drives Stronger Vision Learners](https://mlsanity.com/paper/2310.13593/) (2023)

## Abstract (arXiv)

Masked image modeling (MIM) has attracted much research attention due to its promising potential for learning scalable visual representations. In typical approaches, models usually focus on predicting specific contents of masked patches, and their performances are highly related to pre-defined mask strategies. Intuitively, this procedure can be considered as training a student (the model) on solving given problems (predict masked patches). However, we argue that the model should not only focus on solving given problems, but also stand in the shoes of a teacher to produce a more challenging problem by itself. To this end, we propose Hard Patches Mining (HPM), a brand-new framework for MIM pre-training. We observe that the reconstruction loss can naturally be the metric of the difficulty of the pre-training task. Therefore, we introduce an auxiliary loss predictor, predicting patch-wise losses first and deciding where to mask next. It adopts a relative relationship learning strategy to prevent overfitting to exact reconstruction loss values. Experiments under various settings demonstrate the effectiveness of HPM in constructing masked images. Furthermore, we empirically find that solely introducing the loss prediction objective leads to powerful representations, verifying the efficacy of the ability to be aware of where is hard to reconstruct.