paper-with-me

Papers

What Do You See in Common? Learning Hierarchical Prototypes over Tree-of-Life to Discover Evolutionary Traits

2024-09-03 · Harish Babu Manogaran, M. Maruf, Arka Daw, Kazi Sajeed Mehrab, Caleb Patrick Charpentier, Josef C. Uyeda, Wasila Dahdul, Matthew J Thompson, Elizabeth G Campolongo, Kaiya L Provost, Paula M. Mabee, Hilmar Lapp, Anuj Karpatne

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 features at internal nodes. To overcome these challenges, we introduce the framework of Hierarchy aligned Commonality through Prototypical Networks (HComP-Net). We empirically show that HComP-Net learns prototypes that are accurate, semantically consistent, and generalizable to unseen species in comparison to baselines on birds, butterflies, and fishes datasets. The code and datasets are available at https://github.com/Imageomics/HComPNet.

📄 PDF Abstract BibTeX arXiv:2409.02335

Code (1)

imageomics/hcompnet 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Progressive Tree-Structured Prototype Network for End-to-End Image Captioning

2022-11-17 · Pengpeng Zeng, Jinkuan Zhu, Jingkuan Song, Lianli Gao

Studies of image captioning are shifting towards a trend of a fully end-to-end paradigm by leveraging powerful visual pre-trained models and transformer-based generation architecture for more flexible model training and …

Image Captioning

Deep Taxonomic Networks for Unsupervised Hierarchical Prototype Discovery

2025-09-28 · Zekun Wang, Ethan Haarer, Tianyi Zhu, Zhiyi Dai 외 arxiv

Inspired by the human ability to learn and organize knowledge into hierarchical taxonomies with prototypes, this paper addresses key limitations in current deep hierarchical clustering methods. Existing methods often tie…

Image Classification

Hyperbolic Busemann Learning with Ideal Prototypes

2021-06-28 · NeurIPS 2021 12 · Mina Ghadimi Atigh, Martin Keller-Ressel, Pascal Mettes

Hyperbolic space has become a popular choice of manifold for representation learning of various datatypes from tree-like structures and text to graphs. Building on the success of deep learning with prototypes in Euclidea…

PositionRepresentation Learning

Tree Space Prototypes: Another Look at Making Tree Ensembles Interpretable

2016-11-22 · Sarah Tan, Matvey Soloviev, Giles Hooker, Martin T. Wells

Ensembles of decision trees perform well on many problems, but are not interpretable. In contrast to existing approaches in interpretability that focus on explaining relationships between features and predictions, we pro…

Prototype Selection

Hierarchical Semantic Retrieval with Cobweb

2025-10-02 · Anant Gupta, Karthik Singaravadivelan, Zekun Wang arxiv

Neural document retrieval often treats a corpus as a flat cloud of vectors scored at a single granularity, leaving corpus structure underused and explanations opaque. We use Cobweb--a hierarchy-aware framework--to organi…

Semantic Retrieval