Learning optimally separated class-specific subspace representations using convolutional autoencoder
In this work, we propose a novel convolutional autoencoder based architecture to generate subspace specific feature representations that are best suited for classification task. The class-specific data is assumed to lie in low dimensional linear subspaces, which could be noisy and not well separated, i.e., subspace distance (principal angle) between two classes is very low. The proposed network uses a novel class-specific self expressiveness (CSSE) layer sandwiched between encoder and decoder networks to generate class-wise subspace representations which are well separated. The CSSE layer along with encoder/ decoder are trained in such a way that data still lies in subspaces in the feature space with minimum principal angle much higher than that of the input space. To demonstrate the effectiveness of the proposed approach, several experiments have been carried out on state-of-the-art machine learning datasets and a significant improvement in classification performance is observed over existing subspace based transformation learning methods.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderSimilar Papers 제목 키워드 기반
Towards Clustering-friendly Representations: Subspace Clustering via Graph Filtering
Finding a suitable data representation for a specific task has been shown to be crucial in many applications. The success of subspace clustering depends on the assumption that the data can be separated into different sub…
ClusteringGraph SimilarityLearning task-specific subspaces via interventional post-training of speech foundation models
Speech foundation models, pre-trained on large corpora of unlabelled speech data, produce general-purpose representations which are useful across tasks. However, these representations encode information about salient spe…
Contrastive LearningSpeaker VerificationKeyword SpottingRaSE: Random Subspace Ensemble Classification
We propose a flexible ensemble classification framework, Random Subspace Ensemble (RaSE), for sparse classification. In the RaSE algorithm, we aggregate many weak learners, where each weak learner is a base classifier tr…
ClassificationGeneral ClassificationClass Mean Vector Component and Discriminant Analysis
The kernel matrix used in kernel methods encodes all the information required for solving complex nonlinear problems defined on data representations in the input space using simple, but implicitly defined, solutions. Spe…
Dimensionality ReductionContinuous Manifold Based Adaptation for Evolving Visual Domains
We pose the following question: what happens when test data not only differs from training data, but differs from it in a continually evolving way? The classic domain adaptation paradigm considers the world to be separat…
Domain Adaptation