# Curriculum Learning with Diversity for Supervised Computer Vision Tasks

arXiv: https://arxiv.org/abs/2009.10625 · HTML: https://mlsanity.com/paper/2009.10625/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Sep 2020.

## Built on by (most cited first, 9 of 9)

- [Curriculum Learning: A Survey](https://mlsanity.com/paper/2101.10382/) (2021)
- [Which Samples Should be Learned First: Easy or Hard?](https://mlsanity.com/paper/2110.05481/) (2021)
- [Stochastic Re-weighted Gradient Descent via Distributionally Robust Optimization](https://mlsanity.com/paper/2306.09222/) (2023)
- [Data Optimization in Deep Learning: A Survey](https://mlsanity.com/paper/2310.16499/) (2023)
- [Refining Context-Entangled Content Segmentation via Curriculum Selection and Anti-Curriculum Promotion](https://mlsanity.com/paper/2602.01183/) (2026)
- [Do Data-based Curricula Work?](https://mlsanity.com/paper/2112.06510/) (2021)
- [Exploring Curriculum Learning for Vision-Language Tasks: A Study on Small-Scale Multimodal Training](https://mlsanity.com/paper/2410.15509/) (2024)
- [Vygotsky Distance: Measure for Benchmark Task Similarity](https://mlsanity.com/paper/2402.14890/) (2024)
- [Quantum Curriculum Learning](https://mlsanity.com/paper/2407.02419/) (2024)

## Abstract (arXiv)

Curriculum learning techniques are a viable solution for improving the accuracy of automatic models, by replacing the traditional random training with an easy-to-hard strategy. However, the standard curriculum methodology does not automatically provide improved results, but it is constrained by multiple elements like the data distribution or the proposed model. In this paper, we introduce a novel curriculum sampling strategy which takes into consideration the diversity of the training data together with the difficulty of the inputs. We determine the difficulty using a state-of-the-art estimator based on the human time required for solving a visual search task. We consider this kind of difficulty metric to be better suited for solving general problems, as it is not based on certain task-dependent elements, but more on the context of each image. We ensure the diversity during training, giving higher priority to elements from less visited classes. We conduct object detection and instance segmentation experiments on Pascal VOC 2007 and Cityscapes data sets, surpassing both the randomly-trained baseline and the standard curriculum approach. We prove that our strategy is very efficient for unbalanced data sets, leading to faster convergence and more accurate results, when other curriculum-based strategies fail.