DMS: Differentiable Mean Shift for Dataset Agnostic Task Specific Clustering Using Side Information
Not on the map. Why?
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.
Key facts. Cited by 1 paper 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
18 of 48 references.
References · 18
- 2015Unsupervised Deep Embedding for Clustering Analysiscited by 767
- 2016Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clusteringcited by 237
- 2019Learning to Discover Novel Visual Categories via Deep Transfer Clusteringcited by 225
- 2016Joint Unsupervised Learning of Deep Representations and Image Clusterscited by 205
- 2017Learning Discrete Representations via Information Maximizing Self-Augmented Trainingcited by 149
- 2020Automatically Discovering and Learning New Visual Categories with Ranking Statisticscited by 143
- 2017Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimizationcited by 113
- 2017Recurrent Pixel Embedding for Instance Groupingcited by 58
- 2018Clustering with Deep Learning: Taxonomy and New Methodscited by 46
- 2017Clustering with Noisy Queriescited by 34
- 2017Discriminatively Boosted Image Clustering with Fully Convolutional Auto-Encoderscited by 32
- 2015Neural network-based clustering using pairwise constraintscited by 22
6 more
- 2018Deep Continuous Clusteringcited by 21
- 2017Query Complexity of Clustering with Side Informationcited by 20
- 2017CNN-Based Joint Clustering and Representation Learning with Feature Drift Compensation for Large-Scale Image Datacited by 16
- 2017Approximate Correlation Clustering Using Same-Cluster Queriescited by 11
- 2018Clustering-driven Deep Embedding with Pairwise Constraintscited by 10
- 2017Relaxed Oracles for Semi-Supervised Clusteringcited by 4
Built on by
Citing papers per year: 2023: 1.
1 paper.