# CBM: Curriculum by Masking

arXiv: https://arxiv.org/abs/2407.05193 · HTML: https://mlsanity.com/paper/2407.05193/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 57 references that are in the map.
- First posted on arXiv 6 Jul 2024.

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

- [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)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [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)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [Deep Speech 2: End-to-End Speech Recognition in English and Mandarin](https://mlsanity.com/paper/1512.02595/) (2015)
- [Masked Autoencoders As Spatiotemporal Learners](https://mlsanity.com/paper/2205.09113/) (2022)
- [CSPNet: A New Backbone that can Enhance Learning Capability of CNN](https://mlsanity.com/paper/1911.11929/) (2019)
- [Scaling Language-Image Pre-training via Masking](https://mlsanity.com/paper/2212.00794/) (2022)
- [On The Power of Curriculum Learning in Training Deep Networks](https://mlsanity.com/paper/1904.03626/) (2019)
- [Curriculum Learning: A Survey](https://mlsanity.com/paper/2101.10382/) (2021)
- [Competence-based Curriculum Learning for Neural Machine Translation](https://mlsanity.com/paper/1903.09848/) (2019)
- [Webly Supervised Learning of Convolutional Networks](https://mlsanity.com/paper/1505.01554/) (2015)
- [Curriculum Learning of Multiple Tasks](https://mlsanity.com/paper/1412.1353/) (2014)
- [Curriculum Learning and Minibatch Bucketing in Neural Machine Translation](https://mlsanity.com/paper/1707.09533/) (2017)
- [Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives](https://mlsanity.com/paper/1905.10847/) (2019)
- [How hard can it be? Estimating the difficulty of visual search in an image](https://mlsanity.com/paper/1705.08280/) (2017)
- [Audiovisual Masked Autoencoders](https://mlsanity.com/paper/2212.05922/) (2022)
- [Visualizing and Understanding Curriculum Learning for Long Short-Term Memory Networks](https://mlsanity.com/paper/1611.06204/) (2016)
- [AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders](https://mlsanity.com/paper/2211.09120/) (2022)
- [EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones](https://mlsanity.com/paper/2211.09703/) (2022)
- [Learning to Teach with Dynamic Loss Functions](https://mlsanity.com/paper/1810.12081/) (2018)
- [Curriculum Self-Paced Learning for Cross-Domain Object Detection](https://mlsanity.com/paper/1911.06849/) (2019)
- [Curriculum-based transfer learning for an effective end-to-end spoken language understanding and domain portability](https://mlsanity.com/paper/1906.07601/) (2019)

## Built on by (most cited first, 3 of 3)

- [Masked Image Modeling: A Survey](https://mlsanity.com/paper/2408.06687/) (2024)
- [Adaptively Point-weighting Curriculum Learning](https://mlsanity.com/paper/2505.01665/) (2025)
- [Automated Histopathologic Assessment of Hirschsprung Disease Using a Multi-Stage Vision Transformer Framework](https://mlsanity.com/paper/2511.20734/) (2025)

## Abstract (arXiv)

We propose Curriculum by Masking (CBM), a novel state-of-the-art curriculum learning strategy that effectively creates an easy-to-hard training schedule via patch (token) masking, offering significant accuracy improvements over the conventional training regime and previous curriculum learning (CL) methods. CBM leverages gradient magnitudes to prioritize the masking of salient image regions via a novel masking algorithm and a novel masking block. Our approach enables controlling sample difficulty via the patch masking ratio, generating an effective easy-to-hard curriculum by gradually introducing harder samples as training progresses. CBM operates with two easily configurable parameters, i.e. the number of patches and the curriculum schedule, making it a versatile curriculum learning approach for object recognition and detection. We conduct experiments with various neural architectures, ranging from convolutional networks to vision transformers, on five benchmark data sets (CIFAR-10, CIFAR-100, ImageNet, Food-101 and PASCAL VOC), to compare CBM with conventional as well as curriculum-based training regimes. Our results reveal the superiority of our strategy compared with the state-of-the-art curriculum learning regimes. We also observe improvements in transfer learning contexts, where CBM surpasses previous work by considerable margins in terms of accuracy. We release our code for free non-commercial use at https://github.com/CroitoruAlin/CBM.