# Maximum Entropy Subspace Clustering Network

arXiv: https://arxiv.org/abs/2012.03176 · HTML: https://mlsanity.com/paper/2012.03176/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Dec 2020.

## Built on by (most cited first, 9 of 9)

- [Attention-driven Graph Clustering Network](https://mlsanity.com/paper/2108.05499/) (2021)
- [Deep Attention-guided Graph Clustering with Dual Self-supervision](https://mlsanity.com/paper/2111.05548/) (2021)
- [Adaptive Attribute and Structure Subspace Clustering Network](https://mlsanity.com/paper/2109.13742/) (2021)
- [A Square Peg in a Square Hole: Meta-Expert for Long-Tailed Semi-Supervised Learning](https://mlsanity.com/paper/2505.16341/) (2025)
- [Adaptive Graph Convolutional Subspace Clustering](https://mlsanity.com/paper/2305.03414/) (2023)
- [EGRC-Net: Embedding-induced Graph Refinement Clustering Network](https://mlsanity.com/paper/2211.10627/) (2022)
- [Self-Supervised Deep Subspace Clustering with Entropy-norm](https://mlsanity.com/paper/2206.04958/) (2022)
- [Learning Structure Aware Deep Spectral Embedding](https://mlsanity.com/paper/2305.08215/) (2023)
- [Label-independent hyperparameter-free self-supervised single-view deep subspace clustering](https://mlsanity.com/paper/2504.18179/) (2025)

## Abstract (arXiv)

Deep subspace clustering networks have attracted much attention in subspace clustering, in which an auto-encoder non-linearly maps the input data into a latent space, and a fully connected layer named self-expressiveness module is introduced to learn the affinity matrix via a typical regularization term (e.g., sparse or low-rank). However, the adopted regularization terms ignore the connectivity within each subspace, limiting their clustering performance. In addition, the adopted framework suffers from the coupling issue between the auto-encoder module and the self-expressiveness module, making the network training non-trivial. To tackle these two issues, we propose a novel deep subspace clustering method named Maximum Entropy Subspace Clustering Network (MESC-Net). Specifically, MESC-Net maximizes the entropy of the affinity matrix to promote the connectivity within each subspace, in which its elements corresponding to the same subspace are uniformly and densely distributed. Furthermore, we design a novel framework to explicitly decouple the auto-encoder module and the self-expressiveness module. We also theoretically prove that the learned affinity matrix satisfies the block-diagonal property under the independent subspaces. Extensive quantitative and qualitative results on commonly used benchmark datasets validate MESC-Net significantly outperforms state-of-the-art methods.