Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Label-independent hyperparameter-free self-supervised single-view deep subspace clustering

About

Deep subspace clustering (DSC) algorithms face several challenges that hinder their widespread adoption across variois application domains. First, clustering quality is typically assessed using only the encoder's output layer, disregarding valuable information present in the intermediate layers. Second, most DSC approaches treat representation learning and subspace clustering as independent tasks, limiting their effectiveness. Third, they assume the availability of a held-out dataset for hyperparameter tuning, which is often impractical in real-world scenarios. Fourth, learning termination is commonly based on clustering error monitoring, requiring external labels. Finally, their performance often depends on post-processing techniques that rely on labeled data. To address this limitations, we introduce a novel single-view DSC approach that: (i) minimizes a layer-wise self expression loss using a joint representation matrix; (ii) optimizes a subspace-structured norm to enhance clustering quality; (iii) employs a multi-stage sequential learning framework, consisting of pre-training and fine-tuning, enabling the use of multiple regularization terms without hyperparameter tuning; (iv) incorporates a relative error-based self-stopping mechanism to terminate training without labels; and (v) retains a fixed number of leading coefficients in the learned representation matrix based on prior knowledge. We evaluate the proposed method on six datasets representing faces, digits, and objects. The results show that our method outperforms most linear SC algorithms with careffulyl tuned hyperparameters while maintaining competitive performance with the best performing linear appoaches.

Lovro Sindicic, Ivica Kopriva• 2025

Related benchmarks

TaskDatasetResultRank
ClusteringMNIST (test)
NMI0.6601
154
ClusteringORL
NMI0.8988
44
ClusteringCOIL20
Accuracy82.99
20
ClusteringUSPS
Accuracy (ACC)80.82
19
ClusteringExtended YaleB
Accuracy (ACC)91.61
18
ClusteringCOIL100
ACC52.03
18
Showing 6 of 6 rows

Other info

Follow for update