Due to the long-range modeling ability and linear complexity property, Mamba has attracted considerable attention in point cloud analysis. Despite some interesting progress, related work still suffers from imperfect point cloud serialization, insufficient high-level geometric perception, and overfitting of the selective state space model (S6) at the core of Mamba. To this end, we resort to an SSM-based point cloud network termed CloudMamba to address the above challenges. Specifically, we propose sequence expanding and sequence merging, where the former serializes points along each axis separately and the latter serves to fuse the corresponding higher-order features causally inferred from different sequences, enabling unordered point sets to adapt more stably to the causal nature of Mamba without parameters. Meanwhile, we design chainedMamba that chains the forward and backward processes in the parallel bidirectional Mamba, capturing high-level geometric information during scanning. In addition, we propose a grouped selective state space model (GS6) via parameter sharing on S6, alleviating the overfitting problem caused by the computational mode in S6. Experiments on various point cloud tasks validate CloudMamba's ability to achieve state-of-the-art results with significantly less complexity.

The attention mechanism has become a dominant operator in point cloud learning, but its quadratic complexity leads to limited inter-point interactions, hindering long-range dependency modeling between objects. Due to excellent long-range modeling capability with linear complexity, the selective state space model (S6), as the core of Mamba, has been exploited in point cloud learning for long-range dependency interactions over the entire point cloud. Despite some significant progress, related works still suffer from imperfect point cloud serialization and lack of locality learning. To this end, we explore a state space model-based point cloud network termed HydraMamba to address the above challenges. Specifically, we design a shuffle serialization strategy, making unordered point sets better adapted to the causal nature of S6. Meanwhile, to overcome the deficiency of existing techniques in locality learning, we propose a ConvBiS6 layer, which is capable of capturing local geometries and global context dependencies synergistically. Besides, we propose MHS6 by extending the multi-head design to S6, further enhancing its modeling capability. HydraMamba achieves state-of-the-art results on various tasks at both object-level and scene-level. The code is available at https://github.com/Point-Cloud-Learning/HydraMamba.

The performance of the neighborhood rough set model in feature selection is limited by nonobjective parameter selection method, the uncertainty measures considered only from a single view, and high time cost caused by processing high-dimensional data. To solve the above problems, this study first defines the interclass boundary to granulate the samples in different classes, and three types of neighborhood concepts—negative perspective, neutral perspective, and positive perspective—are put forward based on different cognitive perspectives. Then, the concept of the multiperspective rough set model is developed. The most prominent feature of this model is the discovery of differences between classes from the given data, without any parameters. Second, by integrating the information theory and algebraic views under the multiperspective rough set model, multiview entropy measures are proposed to effectively measure the uncertainty in data. Moreover, a nonmonotonic feature selection algorithm based on the mutual information in the multiview entropy measures under the neutral perspective as the evaluation function of feature importance is designed to resolve the disadvantages of the algorithms based on the monotone evaluation function. Finally, Information Gain is introduced to preliminarily decrease the dimension of high-dimensional data sets to promote classification accuracy and reduce time consumption. The experimental results confirm that the proposed algorithm is efficient in eliminating noise and increasing classification accuracy.