通过树形演化结构学习生物特征原型，发现跨物种的进化共性。
What Do You See in Common? Learning Hierarchical Prototypes over Tree-of-Life to Discover Evolutionary Traits
- 基于演化树结构设计分层原型网络，避免内部节点原型过专
- 在多个数据集上实现更高准确率与泛化能力，优于基线方法
- 适合研究生物演化、图像特征提取的学者使用
生物学中的一个重大挑战是发现进化特征——即在具有共同祖先的物种群中普遍存在的生物特征。随着生物图像库的不断增长，直接从图像中发现具有层次结构的进化特征成为可能。然而，现有基于原型的方法多适用于扁平类别结构，在发现分层原型时面临内部节点原型过专等问题。为此，本文提出层级对齐共性原型网络（HComP-Net），其关键创新包括：一种新型过专性损失以避免内部节点学习到过专原型；一种新型判别性损失，确保某节点原型不在不同谱系的对比物种中出现；以及一种掩码模块，可在不损害分类性能的前提下排除高层级的过专原型。实验表明，相比基线方法，HComP-Net学习到的原型更具准确性、语义一致性，并能泛化至未见物种。
原文摘要 · Abstract (English)
A grand challenge in biology is to discover evolutionary traits - features of organisms common to a group of species with a shared ancestor in the tree of life (also referred to as phylogenetic tree). With the growing availability of image repositories in biology, there is a tremendous opportunity to discover evolutionary traits directly from images in the form of a hierarchy of prototypes. However, current prototype-based methods are mostly designed to operate over a flat structure of classes and face several challenges in discovering hierarchical prototypes, including the issue of learning over-specific prototypes at internal nodes. To overcome these challenges, we introduce the framework of Hierarchy aligned Commonality through Prototypical Networks (HComP-Net). The key novelties in HComP-Net include a novel over-specificity loss to avoid learning over-specific prototypes, a novel discriminative loss to ensure prototypes at an internal node are absent in the contrasting set of species with different ancestry, and a novel masking module to allow for the exclusion of over-specific prototypes at higher levels of the tree without hampering classification performance. We empirically show that HComP-Net learns prototypes that are accurate, semantically consistent, and generalizable to unseen species in comparison to baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。