RDEIC-LFW-DSS: ResNet-based deep embedded image clustering using local feature weighting and dynamic sample selection mechanism

• Published in: Information sciences 2023-10, Vol.646, p.119374, Article 119374
• Main Authors: Golzari Oskouei, Amin, Balafar, Mohammad Ali, Motamed, Cina
• Format: Article
• Language: English
• Subjects: Deep embedded clustering; Local feature weighting; Unsupervised learning
• ISSN: 0020-0255
• DOI: 10.1016/j.ins.2023.119374

•We introduce a ResNet-based deep embedded image clustering framework namely RDEIC-LFW-DSS.•Elaborating a novel ResNet-based embedded clustering, which introduces a mechanism for better network training.•An efficient local representation weighting mechanism is used to properly weight the features of each cluster.•The samples and their neighbors are involved in the learning representations procedure to generate better cluster-oriented meaningful representation. In existing deep clustering methods, as the model gets deeper, extracted representations can be deteriorated due to a vanishing gradient, leading to reduced performance. Also, existing deep clustering frameworks may distort the hidden space without true labels by learning from unreliable estimated pseudo-labels. Therefore, the model learns non-discriminative features from the early epochs, which results in worse estimated pseudo-labels. Moreover, in these models, it is assumed that all learned representations in the bottleneck layer have equal significance throughout the clustering procedure. To address the shortcomings, this paper introduces RDEIC-LFW-DSS, a ResNet-based deep embedded clustering framework. The advantage of residual connection is that it enables the user to add residual connections for increased model capacity without incurring the cost of degradation for unsupervised feature learning compared to standard autoencoders. Furthermore, an efficient local feature weighting mechanism is used to weight each cluster's representations correctly. In addition, we introduce a mechanism in which suitable samples with highly reliable estimated labels are selected to train the deep clustering framework. Extensive experiments conducted on benchmark datasets and comparisons with state-of-the-art approaches confirm the high performance of RDEIC-LFW-DSS. The implementation- source code- of RDEIC-LFW-DSS is made publicly accessible at https://github.com/Amin-Golzari-Oskouei/RDEIC-LFW-DSS.