# Overcomplete Deep Subspace Clustering Networks

arXiv: https://arxiv.org/abs/2011.08306 · HTML: https://mlsanity.com/paper/2011.08306/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2020.

## Built on by (most cited first, 7 of 7)

- [Over-and-Under Complete Convolutional RNN for MRI Reconstruction](https://mlsanity.com/paper/2106.08886/) (2021)
- [Hyperspectral Pansharpening Based on Improved Deep Image Prior and Residual Reconstruction](https://mlsanity.com/paper/2107.02630/) (2021)
- [Aligning Motion-Blurred Images Using Contrastive Learning on Overcomplete Pixels](https://mlsanity.com/paper/2410.07410/) (2024)
- [Learning Structure Aware Deep Spectral Embedding](https://mlsanity.com/paper/2305.08215/) (2023)
- [Semi-overcomplete convolutional auto-encoder embedding as shape priors for deep vessel segmentation](https://mlsanity.com/paper/2409.13001/) (2024)
- [Scalable Context-Preserving Model-Aware Deep Clustering for Hyperspectral Images](https://mlsanity.com/paper/2506.11377/) (2025)
- [Stable Single-Pixel Contrastive Learning for Semantic and Geometric Tasks](https://mlsanity.com/paper/2512.04970/) (2025)

## Abstract (arXiv)

Deep Subspace Clustering Networks (DSC) provide an efficient solution to the problem of unsupervised subspace clustering by using an undercomplete deep auto-encoder with a fully-connected layer to exploit the self expressiveness property. This method uses undercomplete representations of the input data which makes it not so robust and more dependent on pre-training. To overcome this, we propose a simple yet efficient alternative method - Overcomplete Deep Subspace Clustering Networks (ODSC) where we use overcomplete representations for subspace clustering. In our proposed method, we fuse the features from both undercomplete and overcomplete auto-encoder networks before passing them through the self-expressive layer thus enabling us to extract a more meaningful and robust representation of the input data for clustering. Experimental results on four benchmark datasets show the effectiveness of the proposed method over DSC and other clustering methods in terms of clustering error. Our method is also not as dependent as DSC is on where pre-training should be stopped to get the best performance and is also more robust to noise. Code - hrefhttps://github.com/jeya-maria-jose/Overcomplete-Deep-Subspace-Clusteringhttps://github.com/jeya-maria-jose/Overcomplete-Deep-Subspace-Clustering