# LSD-C: Linearly Separable Deep Clusters

arXiv: https://arxiv.org/abs/2006.10039 · HTML: https://mlsanity.com/paper/2006.10039/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2020.

## Built on by (most cited first, 16 of 16)

- [A Unified Objective for Novel Class Discovery](https://mlsanity.com/paper/2108.08536/) (2021)
- [Neighborhood Contrastive Learning for Novel Class Discovery](https://mlsanity.com/paper/2106.10731/) (2021)
- [AutoNovel: Automatically Discovering and Learning Novel Visual Categories](https://mlsanity.com/paper/2106.15252/) (2021)
- [Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation](https://mlsanity.com/paper/2107.03358/) (2021)
- [Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discovery](https://mlsanity.com/paper/2305.06144/) (2023)
- [Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2104.09415/) (2021)
- [Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Data](https://mlsanity.com/paper/2104.12673/) (2021)
- [Interactiveness Field in Human-Object Interactions](https://mlsanity.com/paper/2204.07718/) (2022)
- [New Intent Discovery with Pre-training and Contrastive Learning](https://mlsanity.com/paper/2205.12914/) (2022)
- [CLIP-GCD: Simple Language Guided Generalized Category Discovery](https://mlsanity.com/paper/2305.10420/) (2023)
- [SCALE: Online Self-Supervised Lifelong Learning without Prior Knowledge](https://mlsanity.com/paper/2208.11266/) (2022)
- [Adaptive Betweenness Clustering for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2401.11448/) (2024)
- [Traffic Scenario Clustering by Iterative Optimisation of Self-Supervised Networks Using a Random Forest Activation Pattern Similarity](https://mlsanity.com/paper/2105.07639/) (2021)
- [High-dimensional Clustering onto Hamiltonian Cycle](https://mlsanity.com/paper/2304.14531/) (2023)
- [GMM-IL: Image Classification using Incrementally Learnt, Independent Probabilistic Models for Small Sample Sizes](https://mlsanity.com/paper/2212.00572/) (2022)
- [DeepVAT: A Self-Supervised Technique for Cluster Assessment in Image Datasets](https://mlsanity.com/paper/2306.00011/) (2023)

## Abstract (arXiv)

We present LSD-C, a novel method to identify clusters in an unlabeled dataset. Our algorithm first establishes pairwise connections in the feature space between the samples of the minibatch based on a similarity metric. Then it regroups in clusters the connected samples and enforces a linear separation between clusters. This is achieved by using the pairwise connections as targets together with a binary cross-entropy loss on the predictions that the associated pairs of samples belong to the same cluster. This way, the feature representation of the network will evolve such that similar samples in this feature space will belong to the same linearly separated cluster. Our method draws inspiration from recent semi-supervised learning practice and proposes to combine our clustering algorithm with self-supervised pretraining and strong data augmentation. We show that our approach significantly outperforms competitors on popular public image benchmarks including CIFAR 10/100, STL 10 and MNIST, as well as the document classification dataset Reuters 10K.