Multi-Level Representation Learning for Deep Subspace Clustering
This work addresses subspace clustering, a key problem in unsupervised learning for computer vision and data analysis, with incremental improvements over existing methods.
The paper tackles the problem of subspace clustering by proposing a deep learning approach that uses convolutional autoencoders with multi-level connections and a novel loss function, achieving superior performance on four real-world datasets compared to state-of-the-art methods.
This paper proposes a novel deep subspace clustering approach which uses convolutional autoencoders to transform input images into new representations lying on a union of linear subspaces. The first contribution of our work is to insert multiple fully-connected linear layers between the encoder layers and their corresponding decoder layers to promote learning more favorable representations for subspace clustering. These connection layers facilitate the feature learning procedure by combining low-level and high-level information for generating multiple sets of self-expressive and informative representations at different levels of the encoder. Moreover, we introduce a novel loss minimization problem which leverages an initial clustering of the samples to effectively fuse the multi-level representations and recover the underlying subspaces more accurately. The loss function is then minimized through an iterative scheme which alternatively updates the network parameters and produces new clusterings of the samples. Experiments on four real-world datasets demonstrate that our approach exhibits superior performance compared to the state-of-the-art methods on most of the subspace clustering problems.