# Learning Embeddings for Image Clustering: An Empirical Study of Triplet Loss Approaches

arXiv: https://arxiv.org/abs/2007.03123 · HTML: https://mlsanity.com/paper/2007.03123/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jul 2020.

## Built on by (most cited first, 6 of 6)

- [Deep Clustering via Center-Oriented Margin Free-Triplet Loss for Skin Lesion Detection in Highly Imbalanced Datasets](https://mlsanity.com/paper/2204.02275/) (2022)
- [Training Dynamic based data filtering may not work for NLP datasets](https://mlsanity.com/paper/2109.09191/) (2021)
- [I Spy With My Little Eye: A Minimum Cost Multicut Investigation of Dataset Frames](https://mlsanity.com/paper/2412.01296/) (2024)
- [Estimating the Robustness of Classification Models by the Structure of the Learned Feature-Space](https://mlsanity.com/paper/2106.12303/) (2021)
- [Correlation Clustering of Bird Sounds](https://mlsanity.com/paper/2306.09906/) (2023)
- [ClimateVID -- Social Media Videos Analysis and Challenges Involved](https://mlsanity.com/paper/2604.27968/) (2026)

## Abstract (arXiv)

In this work, we evaluate two different image clustering objectives, k-means clustering and correlation clustering, in the context of Triplet Loss induced feature space embeddings. Specifically, we train a convolutional neural network to learn discriminative features by optimizing two popular versions of the Triplet Loss in order to study their clustering properties under the assumption of noisy labels. Additionally, we propose a new, simple Triplet Loss formulation, which shows desirable properties with respect to formal clustering objectives and outperforms the existing methods. We evaluate all three Triplet loss formulations for K-means and correlation clustering on the CIFAR-10 image classification dataset.