Improving Visual Recognition with Hyperbolical Visual Hierarchy Mapping

arXiv:2404.00974v1 Announce Type: new
Abstract: Visual scenes are naturally organized in a hierarchy, where a coarse semantic is recursively comprised of several fine details. Exploring such a visual hierarchy is crucial to recognize the complex relations of visual elements, leading to a comprehensive scene understanding. In this paper, we propose a Visual Hierarchy Mapper (Hi-Mapper), a novel approach for enhancing the structured understanding of the pre-trained Deep Neural Networks (DNNs). Hi-Mapper investigates the hierarchical organization of the visual scene by …

abstract arxiv cs.cv improving mapping paper recognition relations semantic type understanding visual