TL;DR
This paper introduces Overcomplete Deep Subspace Clustering Networks (ODSC), which fuse overcomplete and undercomplete auto-encoder features to improve robustness and accuracy in unsupervised subspace clustering, outperforming existing methods.
Contribution
The paper proposes a novel overcomplete auto-encoder approach for subspace clustering, enhancing robustness and reducing dependence on pre-training compared to traditional undercomplete methods.
Findings
ODSC outperforms DSC and other clustering methods on benchmark datasets.
The method is more robust to noise and less sensitive to pre-training stopping points.
Experimental results demonstrate improved clustering accuracy.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
