Dynamic Clustering Convolutional Neural Network

Convolutional neural networks (CNNs) have been playing a dominant role in computer vision. However, the existing approaches of using local window modeling in popular CNNs lack flexibility and hinder their ability to capture long-range dependencies of objects in an image. To overcome these limitations, we propose a novel CNN architecture, termed Dynamic Clustering Convolutional Neural Network (DCCNeXt). The proposed DCCNeXt takes a unique approach by employing global clustering to group image patches with similar semantics into clusters that are then convolved using the shared convolution kernels. To address the high computational complexity of global clustering, the feature vectors from each patch's subspace are extracted for efficient clustering, which makes the proposed model widely compatible with the downstream vision tasks. The extensive experiments of image classification, object detection, instance segmentation, and semantic segmentation on the benchmark datasets demonstrate that the proposed DCCNeXt outperforms the mainstream Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), Vision Multi-layer Perceptrons (MLPs), Vision Graph Neural Networks (GNNs), and Vision Mambas. We anticipate that this study will provide a new perspective and a promising avenue for the design of convolutional neural networks.

Authors

• Tanzhe Li Key Laboratory of Multimedia Trusted Perception and Effcient Computing, Ministry of Education of China, Xiamen University, China School of Informatics, Xiamen University, China
• Baochang Zhang Hangzhou Research Institute, School of Artificial Intelligence, Beihang University, China Nanchang Institute of Technology, Nanchang, China
• Jiayi Lyu School of Engineering Science, University of Chinese Academy of Sciences, China
• Xiawu Zheng Xiamen University
• Guodong Guo Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, China
• Taisong Jin Key Laboratory of Multimedia Trusted Perception and Effcient Computing, Ministry of Education of China, Xiamen University, China School of Informatics, Xiamen University, China Key Laboratory of Oracle Bone Inscriptions Information Processing, Ministry of Education of China, Anyang Normal University, China

Keywords

No keywords are indexed for this paper.