Look Further to Recognize Better: Learning Shared Topics and Category-Specific Dictionaries for Open-Ended 3D Object Recognition

张宁 Look Further to Recognize Better: Learning Shared Topics and Category-Specific Dictionaries for Open-Ended 3D Object Recognition

进一步看待以更好地识别：学习共享主题和类别专用词典以进行开放式3D对象识别

S. Hamidreza Kasaei
链接：https://pan.baidu.com/s/1HhvMLljfNdzvYrw7p9yk0A
提取码：b1gf

Abstract—Service robots are expected to operate effectively in human-centric environments for long periods of time. In such realistic scenarios, fine-grained object categorization is as important as basic-level object categorization. We tackle this problem by proposing an open-ended object recognition approach which concurrently learns both the object categories and the local features for encoding objects. In this work, each object is represented using a set of general latent visual topics and category-specific dictionaries. The general topics encode the common patterns of all categories, while the category-specific dictionary describes the content of each category in details. The proposed approach discovers both sets of general and specific representations in an unsupervised fashion and updates them incrementally using new object views. Experimental results show that our approach yields significant improvements over the previous state-of-the-art approaches concerning scalability and object classification performance. Moreover, our approach demonstrates the capability of learning from very few training examples in a real-world setting. Regarding computation time, the best result was obtained with a Bag-of-Words method followed by a variant of the Latent Dirichlet Allocation approach.

服务机器人有望在以人为本的环境中长期有效运行。 在这种现实情况下，细粒度的对象分类与基本级别的对象分类一样重要。我们通过提出一种开放式对象识别方法来解决此问题，该方法同时学习对象类别和用于编码对象的局部特征。在这项工作中，每个对象都使用一组通用的潜在视觉主题和特定类别的词典来表示。实验结果表明，与以前有关可伸缩性和对象分类性能的最新方法相比，我们的方法取得了显着改进。此外，我们的方法展示了在实际环境中从很少的训练示例中学习的能力。 关于计算时间，最好的方法是用词袋法，然后再加上潜在的狄利克雷分配法。