# Weakly Supervised Representation Learning with Coarse Labels

arXiv: https://arxiv.org/abs/2005.09681 · HTML: https://mlsanity.com/paper/2005.09681/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 May 2020.

## Built on by (most cited first, 11 of 11)

- [MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset](https://mlsanity.com/paper/2303.12756/) (2023)
- [On Label Granularity and Object Localization](https://mlsanity.com/paper/2207.10225/) (2022)
- [Rapid Network Adaptation: Learning to Adapt Neural Networks Using Test-Time Feedback](https://mlsanity.com/paper/2309.15762/) (2023)
- [Coarse-To-Fine Incremental Few-Shot Learning](https://mlsanity.com/paper/2111.14806/) (2021)
- [Hyperbolic Space with Hierarchical Margin Boosts Fine-Grained Learning from Coarse Labels](https://mlsanity.com/paper/2311.11019/) (2023)
- [Constrained Mean Shift Using Distant Yet Related Neighbors for Representation Learning](https://mlsanity.com/paper/2112.04607/) (2021)
- [Fine-grained Classes and How to Find Them](https://mlsanity.com/paper/2406.11070/) (2024)
- [BackSplit: The Importance of Sub-dividing the Background in Biomedical Lesion Segmentation](https://mlsanity.com/paper/2511.19394/) (2025)
- [Extremely coarse learning objectives induce human-aligned representations in AI vision models](https://mlsanity.com/paper/2605.05556/) (2026)
- [SeA: Semantic Adversarial Augmentation for Last Layer Features from Unsupervised Representation Learning](https://mlsanity.com/paper/2408.13351/) (2024)
- [Latent Softmax for Data-Efficient Phoneme-Based Multilingual ASR Across Tonal and Non-Tonal Languages](https://mlsanity.com/paper/2608.01281/) (2026)

## Abstract (arXiv)

With the development of computational power and techniques for data collection, deep learning demonstrates a superior performance over most existing algorithms on visual benchmark data sets. Many efforts have been devoted to studying the mechanism of deep learning. One important observation is that deep learning can learn the discriminative patterns from raw materials directly in a task-dependent manner. Therefore, the representations obtained by deep learning outperform hand-crafted features significantly. However, for some real-world applications, it is too expensive to collect the task-specific labels, such as visual search in online shopping. Compared to the limited availability of these task-specific labels, their coarse-class labels are much more affordable, but representations learned from them can be suboptimal for the target task. To mitigate this challenge, we propose an algorithm to learn the fine-grained patterns for the target task, when only its coarse-class labels are available. More importantly, we provide a theoretical guarantee for this. Extensive experiments on real-world data sets demonstrate that the proposed method can significantly improve the performance of learned representations on the target task, when only coarse-class information is available for training. Code is available at urlhttps://github.com/idstcv/CoIns.