mlsanityData to 14 Oct 2026

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

arXiv 2409.02335 ↗First posted 3 Sep 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 56 references that are in the map. First posted on arXiv 3 Sep 2024.

Builds on

24 of 56 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2022A ConvNet for the 2020scited by 3,579
  3. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  4. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  5. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,405
  6. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 737
  7. 2021TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentationcited by 227
  8. 2020Concept Whitening for Interpretable Image Recognitioncited by 225
  9. 2020Neural Prototype Trees for Interpretable Fine-grained Image Recognitioncited by 214
  10. 2021Benchmarking Representation Learning for Natural World Image Collectionscited by 168
  11. 2019Orthogonal Convolutional Neural Networkscited by 123
  12. 2021HIVE: Evaluating the Human Interpretability of Visual Explanationscited by 105
12 more
  1. 2021Interpretable Image Classification with Differentiable Prototypes Assignmentcited by 97
  2. 2020ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discoverycited by 89
  3. 2019Interpretable Image Recognition with Hierarchical Prototypescited by 65
  4. 2021This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networkscited by 65
  5. 2023This Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizationscited by 36
  6. 2023A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysiscited by 15
  7. 2024Knowledge-guided Machine Learning: Current Trends and Future Prospectscited by 14
  8. 2015Learning Structured Inference Neural Networks with Label Relationscited by 13
  9. 2021Representation Learning via Consistent Assignment of Views to Clusterscited by 8
  10. 2024Hierarchical Conditioning of Diffusion Models Using Tree-of-Life for Studying Species Evolutioncited by 7
  11. 2023Discovering Novel Biological Traits From Images Using Phylogeny-Guided Neural Networkscited by 5
  12. 2023Hierarchical Semantic Tree Concept Whitening for Interpretable Image Classificationcited by 5

Built on by

Not cited yet.