判别性特征引导的零样本三维模型分类算法  

Discriminative Feature-Guided Zero-Shot Learning of 3D Model Classification Algorithm

作　　者：范有福 白静[1,2] 邵会会 彭斌 Fan Youfu;Bai Jing;Shao Huihui;Peng Bin(School of Computer Science and Engineering,North Minzu University,Yinchuan 750021;The Key Laboratory of Images&Graphics Intelligent Processing of State Ethnic Affairs Commission,Yinchuan 750021)

机构地区：[1]北方民族大学计算机科学与工程学院,银川750021 [2]国家民委图像图形智能处理实验室,银川750021

出　　处：《计算机辅助设计与图形学学报》2024年第2期223-235,共13页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金(61762003,61972121);宁夏自然科学基金(2022AAC02041);宁夏优秀人才支持计划;北方民族大学“计算机视觉和虚拟现实”创新团队.

摘　　要：基于零样本学习的三维模型分类是三维视觉领域的一个新兴话题,旨在对未经训练的三维模型进行正确分类.针对零样本三维模型分类中存在重视全局而忽视局部,强制约束而无视语义-视觉跨域差异性,导致整体性能低下的问题,提出一种判别性特征引导的零样本三维模型分类算法.首先,以三维模型的多视图表征为输入,自适应地捕获三维模型的局部判别性特征,获得具有良好语义对应性的视觉特征表示;其次,以词向量的形式引入类的语义表示,结合条件生成对抗网络生成类的伪视觉特征;最后,提出语义判别损失和内容感知损失联合监督,从语义到内容共同约束真实视觉特征和伪视觉特征的对齐,鼓励模型学习具有高局部判别性的特征,实现语义-视觉的跨域细粒度对齐.在ZS3D数据集上达到了60.9%的Top-1准确率,超越当前最好方法2.3个百分点,同时在Ali数据集的3个子数据集上也分别取得31.9%,9.9%和16.6%的准确率,均达到了较好的实验效果,验证了该算法的有效性和普适性.Zero-shot learning of 3D model classification is a burgeoning topic in the field of 3D vision,aiming to classify untrained 3D models correctly.Aiming at the problem that zero-shot learning of 3D model classifi-cation focus on global information rather than local information,impose mandatory constraints,and ignore the cross-domains semantic-visual differences,resulting in low performance,this paper proposes a discriminative feature-guided zero-short 3D model classification network.Firstly,the local discriminative features,i.e.,real-visual features of the multi-view 3D models,are adaptively captured by the proposed visual feature ex-traction module.Secondly,the semantic representations of the class labels are introduced in the form of word vectors,and their pseudo-visual features are generated by conditional generation adversarial network.Finally,the fine-grained across domains alignment of semantic-visual features is achieved by a novel semantic-content joint loss,which consists of semantic discriminative loss and content-aware loss between real-visual and pseudo-visual features from semantics to contents.The proposed algorithm achieves a Top-1 accuracy rate of 60.9%on the ZS3D dataset,which exceeds with the current best method with an accuracy rate of 2.3 percent-age points.And achieves an accuracy rate of 31.9%,9.9%and 16.6%on the three sub-datasets of Ali,respec-tively,which performs an excellent experimental result and verifies the effectiveness and universality of the proposed algorithm.

关 键 词：三维模型分类 零样本学习 判别性特征 联合损失 细粒度对齐 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]