{"ID":2865228,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.22150","arxiv_id":"2509.22150","title":"Joint graph entropy knowledge distillation for point cloud classification and robustness against corruptions","abstract":"Classification tasks in 3D point clouds often assume that class events \\replaced{are }{follow }independent and identically distributed (IID), although this assumption destroys the correlation between classes. This \\replaced{study }{paper }proposes a classification strategy, \\textbf{J}oint \\textbf{G}raph \\textbf{E}ntropy \\textbf{K}nowledge \\textbf{D}istillation (JGEKD), suitable for non-independent and identically distributed 3D point cloud data, \\replaced{which }{the strategy } achieves knowledge transfer of class correlations through knowledge distillation by constructing a loss function based on joint graph entropy. First\\deleted{ly}, we employ joint graphs to capture add{the }hidden relationships between classes\\replaced{ and}{,} implement knowledge distillation to train our model by calculating the entropy of add{add }graph.\\replaced{ Subsequently}{ Then}, to handle 3D point clouds \\deleted{that is }invariant to spatial transformations, we construct \\replaced{S}{s}iamese structures and develop two frameworks, self-knowledge distillation and teacher-knowledge distillation, to facilitate information transfer between different transformation forms of the same data. \\replaced{In addition}{ Additionally}, we use the above framework to achieve knowledge transfer between point clouds and their corrupted forms, and increase the robustness against corruption of model. Extensive experiments on ScanObject, ModelNet40, ScanntV2\\_cls and ModelNet-C demonstrate that the proposed strategy can achieve competitive results.","short_abstract":"Classification tasks in 3D point clouds often assume that class events \\replaced{are }{follow }independent and identically distributed (IID), although this assumption destroys the correlation between classes. This \\replaced{study }{paper }proposes a classification strategy, \\textbf{J}oint \\textbf{G}raph \\textbf{E}ntrop...","url_abs":"https://arxiv.org/abs/2509.22150","url_pdf":"https://arxiv.org/pdf/2509.22150v1","authors":"[\"Zhiqiang Tian\",\"Weigang Li\",\"Junwei Hu\",\"Chunhua Deng\"]","published":"2025-09-26T10:09:58Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.IR\"]","methods":"[]","has_code":false}