# Coarse-to-Fine Curriculum Learning

arXiv: https://arxiv.org/abs/2106.04072 · HTML: https://mlsanity.com/paper/2106.04072/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 73 references that are in the map.
- First posted on arXiv 8 Jun 2021.

## Builds on (most cited first, 20 of 20)

- [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)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [Competence-based Curriculum Learning for Neural Machine Translation](https://mlsanity.com/paper/1903.09848/) (2019)
- [Reverse Curriculum Generation for Reinforcement Learning](https://mlsanity.com/paper/1707.05300/) (2017)
- [Better Fine-Tuning by Reducing Representational Collapse](https://mlsanity.com/paper/2008.03156/) (2020)
- [Higher-order Coreference Resolution with Coarse-to-fine Inference](https://mlsanity.com/paper/1804.05392/) (2018)
- [Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play](https://mlsanity.com/paper/1703.05407/) (2017)
- [CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images](https://mlsanity.com/paper/1808.01097/) (2018)
- [Coarse-to-Fine Decoding for Neural Semantic Parsing](https://mlsanity.com/paper/1805.04793/) (2018)
- [Curriculum Learning of Multiple Tasks](https://mlsanity.com/paper/1412.1353/) (2014)
- [LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition](https://mlsanity.com/paper/1912.01601/) (2019)
- [Do Convolutional Neural Networks Learn Class Hierarchy?](https://mlsanity.com/paper/1710.06501/) (2017)
- [NBDT: Neural-Backed Decision Trees](https://mlsanity.com/paper/2004.00221/) (2020)
- [Curriculum Learning of Visual Attribute Clusters for Multi-Task Classification](https://mlsanity.com/paper/1709.06664/) (2017)
- [Coarse-to-fine Optimization for Speech Enhancement](https://mlsanity.com/paper/1908.08044/) (2019)
- [Coarse-to-Fine Classification via Parametric and Nonparametric Models for Computer-Aided Diagnosis](https://mlsanity.com/paper/1405.4308/) (2014)

## Built on by (most cited first, 10 of 10)

- [Hyperbolic Space with Hierarchical Margin Boosts Fine-Grained Learning from Coarse Labels](https://mlsanity.com/paper/2311.11019/) (2023)
- [Curriculum-Based Augmented Fourier Domain Adaptation for Robust Medical Image Segmentation](https://mlsanity.com/paper/2306.03511/) (2023)
- [Continual Coarse-to-Fine Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2201.06974/) (2022)
- [Learning from Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2301.11145/) (2023)
- [C2F-CHART: A Curriculum Learning Approach to Chart Classification](https://mlsanity.com/paper/2409.04683/) (2024)
- [Extremely coarse learning objectives induce human-aligned representations in AI vision models](https://mlsanity.com/paper/2605.05556/) (2026)
- [Maneuver Decision-Making For Autonomous Air Combat Through Curriculum Learning And Reinforcement Learning With Sparse Rewards](https://mlsanity.com/paper/2302.05838/) (2023)
- [Maneuver Decision-Making Through Automatic Curriculum Reinforcement Learning Without Handcrafted Reward functions](https://mlsanity.com/paper/2307.06152/) (2023)
- [Hierarchical Scaffolding Enables Human-Like Cognitive Selectivity under Data Scarcity](https://mlsanity.com/paper/2607.04709/) (2026)
- [HASTE: Hierarchical and Attribute-aware Supervision for Generative Recommendation](https://mlsanity.com/paper/2610.17368/) (2026)

## Abstract (arXiv)

When faced with learning challenging new tasks, humans often follow sequences of steps that allow them to incrementally build up the necessary skills for performing these new tasks. However, in machine learning, models are most often trained to solve the target tasks directly.Inspired by human learning, we propose a novel curriculum learning approach which decomposes challenging tasks into sequences of easier intermediate goals that are used to pre-train a model before tackling the target task. We focus on classification tasks, and design the intermediate tasks using an automatically constructed label hierarchy. We train the model at each level of the hierarchy, from coarse labels to fine labels, transferring acquired knowledge across these levels. For instance, the model will first learn to distinguish animals from objects, and then use this acquired knowledge when learning to classify among more fine-grained classes such as cat, dog, car, and truck. Most existing curriculum learning algorithms for supervised learning consist of scheduling the order in which the training examples are presented to the model. In contrast, our approach focuses on the output space of the model. We evaluate our method on several established datasets and show significant performance gains especially on classification problems with many labels. We also evaluate on a new synthetic dataset which allows us to study multiple aspects of our method.