# Deep Discriminative Clustering Analysis

arXiv: https://arxiv.org/abs/1905.01681 · HTML: https://mlsanity.com/paper/1905.01681/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 May 2019.

## Built on by (most cited first, 28 of 28)

- [SPICE: Semantic Pseudo-labeling for Image Clustering](https://mlsanity.com/paper/2103.09382/) (2021)
- [Temporal Action Segmentation: An Analysis of Modern Techniques](https://mlsanity.com/paper/2210.10352/) (2022)
- [Deep Clustering: A Comprehensive Survey](https://mlsanity.com/paper/2210.04142/) (2022)
- [A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directions](https://mlsanity.com/paper/2206.07579/) (2022)
- [Twin Contrastive Learning for Online Clustering](https://mlsanity.com/paper/2210.11680/) (2022)
- [You Never Cluster Alone](https://mlsanity.com/paper/2106.01908/) (2021)
- [Semantic-Enhanced Image Clustering](https://mlsanity.com/paper/2208.09849/) (2022)
- [Clustering by Maximizing Mutual Information Across Views](https://mlsanity.com/paper/2107.11635/) (2021)
- [DivClust: Controlling Diversity in Deep Clustering](https://mlsanity.com/paper/2304.01042/) (2023)
- [DLME: Deep Local-flatness Manifold Embedding](https://mlsanity.com/paper/2207.03160/) (2022)
- [Unsupervised Hyperbolic Representation Learning via Message Passing Auto-Encoders](https://mlsanity.com/paper/2103.16046/) (2021)
- [Strongly Augmented Contrastive Clustering](https://mlsanity.com/paper/2206.00380/) (2022)
- [Deep Clustering by Semantic Contrastive Learning](https://mlsanity.com/paper/2103.02662/) (2021)
- [Information Maximization Clustering via Multi-View Self-Labelling](https://mlsanity.com/paper/2103.07368/) (2021)
- [Doubly Contrastive Deep Clustering](https://mlsanity.com/paper/2103.05484/) (2021)
- [Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach](https://mlsanity.com/paper/2312.14138/) (2023)
- [Representation Learning for Clustering via Building Consensus](https://mlsanity.com/paper/2105.01289/) (2021)
- [C3: Cross-instance guided Contrastive Clustering](https://mlsanity.com/paper/2211.07136/) (2022)
- [Deep Image Clustering with Contrastive Learning and Multi-scale Graph Convolutional Networks](https://mlsanity.com/paper/2207.07173/) (2022)
- [Multi-level Cross-modal Alignment for Image Clustering](https://mlsanity.com/paper/2401.11740/) (2024)
- [Cluster Analysis with Deep Embeddings and Contrastive Learning](https://mlsanity.com/paper/2109.12714/) (2021)
- [Unsupervised Deep Discriminant Analysis Based Clustering](https://mlsanity.com/paper/2206.04686/) (2022)
- [Deep Clustering with Self-Supervision using Pairwise Similarities](https://mlsanity.com/paper/2405.03590/) (2024)
- [GCC: Generative Calibration Clustering](https://mlsanity.com/paper/2404.09115/) (2024)
- [CLUBench: A Clustering Benchmark](https://mlsanity.com/paper/2605.29933/) (2026)
- [Improving Image Clustering through Sample Ranking and Its Application to remote--sensing images](https://mlsanity.com/paper/2209.12621/) (2022)
- [Learning Structure Aware Deep Spectral Embedding](https://mlsanity.com/paper/2305.08215/) (2023)
- [An Adaptor for Triggering Semi-Supervised Learning to Out-of-Box Serve Deep Image Clustering](https://mlsanity.com/paper/2509.20976/) (2025)

## Abstract (arXiv)

Traditional clustering methods often perform clustering with low-level indiscriminative representations and ignore relationships between patterns, resulting in slight achievements in the era of deep learning. To handle this problem, we develop Deep Discriminative Clustering (DDC) that models the clustering task by investigating relationships between patterns with a deep neural network. Technically, a global constraint is introduced to adaptively estimate the relationships, and a local constraint is developed to endow the network with the capability of learning high-level discriminative representations. By iteratively training the network and estimating the relationships in a mini-batch manner, DDC theoretically converges and the trained network enables to generate a group of discriminative representations that can be treated as clustering centers for straightway clustering. Extensive experiments strongly demonstrate that DDC outperforms current methods on eight image, text and audio datasets concurrently.