# Deep Multimodal Subspace Clustering Networks

arXiv: https://arxiv.org/abs/1804.06498 · HTML: https://mlsanity.com/paper/1804.06498/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2018.

## Built on by (most cited first, 30 of 31)

- [Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions](https://mlsanity.com/paper/2209.03430/) (2022)
- [Deep Clustering: A Comprehensive Survey](https://mlsanity.com/paper/2210.04142/) (2022)
- [Multi-level Feature Learning for Contrastive Multi-view Clustering](https://mlsanity.com/paper/2106.11193/) (2021)
- [Reconsidering Representation Alignment for Multi-view Clustering](https://mlsanity.com/paper/2103.07738/) (2021)
- [A Review on Explainability in Multimodal Deep Neural Nets](https://mlsanity.com/paper/2105.07878/) (2021)
- [GCFAgg: Global and Cross-view Feature Aggregation for Multi-view Clustering](https://mlsanity.com/paper/2305.06799/) (2023)
- [Pseudo-supervised Deep Subspace Clustering](https://mlsanity.com/paper/2104.03531/) (2021)
- [Novel Class Discovery: an Introduction and Key Concepts](https://mlsanity.com/paper/2302.12028/) (2023)
- [Self-Supervised Information Bottleneck for Deep Multi-View Subspace Clustering](https://mlsanity.com/paper/2204.12496/) (2022)
- [Unsupervised Manifold Linearizing and Clustering](https://mlsanity.com/paper/2301.01805/) (2023)
- [On the Effects of Self-supervision and Contrastive Alignment in Deep Multi-view Clustering](https://mlsanity.com/paper/2303.09877/) (2023)
- [Selective Pseudo-label Clustering](https://mlsanity.com/paper/2107.10692/) (2021)
- [A Clustering-guided Contrastive Fusion for Multi-view Representation Learning](https://mlsanity.com/paper/2212.13726/) (2022)
- [Federated Deep Multi-View Clustering with Global Self-Supervision](https://mlsanity.com/paper/2309.13697/) (2023)
- [MORI-RAN: Multi-view Robust Representation Learning via Hybrid Contrastive Fusion](https://mlsanity.com/paper/2208.12545/) (2022)
- [Trusted Mamba Contrastive Network for Multi-View Clustering](https://mlsanity.com/paper/2412.16487/) (2024)
- [Latent Code-Based Fusion: A Volterra Neural Network Approach](https://mlsanity.com/paper/2104.04829/) (2021)
- [Attentive Multi-View Deep Subspace Clustering Net](https://mlsanity.com/paper/2112.12506/) (2021)
- [Self-supervised Multi-view Clustering in Computer Vision: A Survey](https://mlsanity.com/paper/2309.09473/) (2023)
- [Self Supervised Correlation-based Permutations for Multi-View Clustering](https://mlsanity.com/paper/2402.16383/) (2024)
- [Beyond Linear Subspace Clustering: A Comparative Study of Nonlinear Manifold Clustering Algorithms](https://mlsanity.com/paper/2103.10656/) (2021)
- [fMBN-E: Efficient Unsupervised Network Structure Ensemble and Selection for Clustering](https://mlsanity.com/paper/2107.02071/) (2021)
- [Information Fusion: Scaling Subspace-Driven Approaches](https://mlsanity.com/paper/2204.12035/) (2022)
- [Self-Supervised Deep Subspace Clustering with Entropy-norm](https://mlsanity.com/paper/2206.04958/) (2022)
- [Efficient and Effective Deep Multi-view Subspace Clustering](https://mlsanity.com/paper/2310.09718/) (2023)
- [Hierarchical Mutual Information Analysis: Towards Multi-view Clustering in The Wild](https://mlsanity.com/paper/2310.18614/) (2023)
- [Towards Generalized Multi-stage Clustering: Multi-view Self-distillation](https://mlsanity.com/paper/2310.18890/) (2023)
- [Multi-View Stochastic Block Models](https://mlsanity.com/paper/2406.04860/) (2024)
- [Federated Deep Subspace Clustering](https://mlsanity.com/paper/2501.00230/) (2024)
- [Multi-view Clustering via Bi-level Decoupling and Consistency Learning](https://mlsanity.com/paper/2508.13499/) (2025)

## Abstract (arXiv)

We present convolutional neural network (CNN) based approaches for unsupervised multimodal subspace clustering. The proposed framework consists of three main stages - multimodal encoder, self-expressive layer, and multimodal decoder. The encoder takes multimodal data as input and fuses them to a latent space representation. The self-expressive layer is responsible for enforcing the self-expressiveness property and acquiring an affinity matrix corresponding to the data points. The decoder reconstructs the original input data. The network uses the distance between the decoder's reconstruction and the original input in its training. We investigate early, late and intermediate fusion techniques and propose three different encoders corresponding to them for spatial fusion. The self-expressive layers and multimodal decoders are essentially the same for different spatial fusion-based approaches. In addition to various spatial fusion-based methods, an affinity fusion-based network is also proposed in which the self-expressive layer corresponding to different modalities is enforced to be the same. Extensive experiments on three datasets show that the proposed methods significantly outperform the state-of-the-art multimodal subspace clustering methods.