Maximum Entropy Subspace Clustering Network
This work provides an incremental improvement for researchers and practitioners working on subspace clustering by enhancing connectivity within subspaces and decoupling network modules.
This paper addresses limitations in deep subspace clustering networks by proposing the Maximum Entropy Subspace Clustering Network (MESC-Net). MESC-Net maximizes the entropy of the affinity matrix to improve within-subspace connectivity and explicitly decouples the auto-encoder and self-expressiveness modules, leading to significant performance improvements over state-of-the-art methods on benchmark datasets.
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.