# DMS: Differentiable Mean Shift for Dataset Agnostic Task Specific Clustering Using Side Information

arXiv: https://arxiv.org/abs/2305.18492 · HTML: https://mlsanity.com/paper/2305.18492/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 48 references that are in the map.
- First posted on arXiv 29 May 2023.

## Builds on (most cited first, 18 of 18)

- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering](https://mlsanity.com/paper/1610.04794/) (2016)
- [Learning to Discover Novel Visual Categories via Deep Transfer Clustering](https://mlsanity.com/paper/1908.09884/) (2019)
- [Joint Unsupervised Learning of Deep Representations and Image Clusters](https://mlsanity.com/paper/1604.03628/) (2016)
- [Learning Discrete Representations via Information Maximizing Self-Augmented Training](https://mlsanity.com/paper/1702.08720/) (2017)
- [Automatically Discovering and Learning New Visual Categories with Ranking Statistics](https://mlsanity.com/paper/2002.05714/) (2020)
- [Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization](https://mlsanity.com/paper/1704.06327/) (2017)
- [Recurrent Pixel Embedding for Instance Grouping](https://mlsanity.com/paper/1712.08273/) (2017)
- [Clustering with Deep Learning: Taxonomy and New Methods](https://mlsanity.com/paper/1801.07648/) (2018)
- [Clustering with Noisy Queries](https://mlsanity.com/paper/1706.07510/) (2017)
- [Discriminatively Boosted Image Clustering with Fully Convolutional Auto-Encoders](https://mlsanity.com/paper/1703.07980/) (2017)
- [Neural network-based clustering using pairwise constraints](https://mlsanity.com/paper/1511.06321/) (2015)
- [Deep Continuous Clustering](https://mlsanity.com/paper/1803.01449/) (2018)
- [Query Complexity of Clustering with Side Information](https://mlsanity.com/paper/1706.07719/) (2017)
- [CNN-Based Joint Clustering and Representation Learning with Feature Drift Compensation for Large-Scale Image Data](https://mlsanity.com/paper/1705.07091/) (2017)
- [Approximate Correlation Clustering Using Same-Cluster Queries](https://mlsanity.com/paper/1712.06865/) (2017)
- [Clustering-driven Deep Embedding with Pairwise Constraints](https://mlsanity.com/paper/1803.08457/) (2018)
- [Relaxed Oracles for Semi-Supervised Clustering](https://mlsanity.com/paper/1711.07433/) (2017)

## Built on by (most cited first, 1 of 1)

- [ABC Easy as 123: A Blind Counter for Exemplar-Free Multi-Class Class-agnostic Counting](https://mlsanity.com/paper/2309.04820/) (2023)

## Abstract (arXiv)

We present a novel approach, in which we learn to cluster data directly from side information, in the form of a small set of pairwise examples. Unlike previous methods, with or without side information, we do not need to know the number of clusters, their centers or any kind of distance metric for similarity. Our method is able to divide the same data points in various ways dependant on the needs of a specific task, defined by the side information. Contrastingly, other work generally finds only the intrinsic, most obvious, clusters. Inspired by the mean shift algorithm, we implement our new clustering approach using a custom iterative neural network to create Differentiable Mean Shift (DMS), a state of the art, dataset agnostic, clustering method. We found that it was possible to train a strong cluster definition without enforcing a constraint that each cluster must be presented during training. DMS outperforms current methods in both the intrinsic and non-intrinsic dataset tasks.