# Beyond Cats and Dogs: Semi-supervised Classification of fuzzy labels with overclustering

arXiv: https://arxiv.org/abs/2012.01768 · HTML: https://mlsanity.com/paper/2012.01768/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2020.

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

- [Is one annotation enough? A data-centric image classification benchmark for noisy and ambiguous label estimation](https://mlsanity.com/paper/2207.06214/) (2022)
- [Ambiguous Images With Human Judgments for Robust Visual Event Classification](https://mlsanity.com/paper/2210.03102/) (2022)
- [A data-centric approach for improving ambiguous labels with combined semi-supervised classification and clustering](https://mlsanity.com/paper/2106.16209/) (2021)
- [Beyond Hard Labels: Investigating data label distributions](https://mlsanity.com/paper/2207.06224/) (2022)
- [Survey of Automatic Plankton Image Recognition: Challenges, Existing Solutions and Future Perspectives](https://mlsanity.com/paper/2305.11739/) (2023)
- [Self-Supervised Pretraining for Fine-Grained Plankton Recognition](https://mlsanity.com/paper/2503.11341/) (2025)
- [Label Smarter, Not Harder: CleverLabel for Faster Annotation of Ambiguous Image Classification with Higher Quality](https://mlsanity.com/paper/2305.12811/) (2023)
- [Opportunistic hip fracture risk prediction in Men from X-ray: Findings from the Osteoporosis in Men (MrOS) Study](https://mlsanity.com/paper/2207.10970/) (2022)
- [Annotating Ambiguous Images: General Annotation Strategy for High-Quality Data with Real-World Biomedical Validation](https://mlsanity.com/paper/2306.12189/) (2023)
- [Life is not black and white -- Combining Semi-Supervised Learning with fuzzy labels](https://mlsanity.com/paper/2110.06592/) (2021)
- [Self-Supervised Federated Learning under Data Heterogeneity for Label-Scarce Diatom Classification](https://mlsanity.com/paper/2603.29633/) (2026)

## Abstract (arXiv)

A long-standing issue with deep learning is the need for large and consistently labeled datasets. Although the current research in semi-supervised learning can decrease the required amount of annotated data by a factor of 10 or even more, this line of research still uses distinct classes like cats and dogs. However, in the real-world we often encounter problems where different experts have different opinions, thus producing fuzzy labels. We propose a novel framework for handling semi-supervised classifications of such fuzzy labels. Our framework is based on the idea of overclustering to detect substructures in these fuzzy labels. We propose a novel loss to improve the overclustering capability of our framework and show on the common image classification dataset STL-10 that it is faster and has better overclustering performance than previous work. On a real-world plankton dataset, we illustrate the benefit of overclustering for fuzzy labels and show that we beat previous state-of-the-art semisupervised methods. Moreover, we acquire 5 to 10% more consistent predictions of substructures.