mlsanityData to 14 Oct 2026

hYOLO Model: Enhancing Object Classification with Hierarchical Context in YOLOv8

arXiv 2510.23278 ↗First posted 27 Oct 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Current convolution neural network (CNN) classification methods are predominantly focused on flat classification which aims solely to identify a specified object within an image. However, real-world objects often possess a natural hierarchical organization that can significantly help classification tasks. Capturing the presence of relations between objects enables better contextual understanding as well as control over the severity of mistakes. Considering these aspects, this paper proposes an end-to-end hierarchical model for image detection and classification built upon the YOLO model family. A novel hierarchical architecture, a modified loss function, and a performance metric tailored to the hierarchical nature of the model are introduced. The proposed model is trained and evaluated on two different hierarchical categorizations of the same dataset: a systematic categorization that disregards visual similarities between objects and a categorization accounting for common visual characteristics across classes. The results illustrate how the suggested methodology addresses the inherent hierarchical structure present in real-world objects, which conventional flat classification algorithms often overlook.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 38 references that are in the map. First posted on arXiv 27 Oct 2025.

Builds on

21 of 38 references.

References · 21

  1. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  2. 2019Distance-IoU Loss: Faster and Better Learning for Bounding Box Regressioncited by 459
  3. 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 409
  4. 2023A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAScited by 151
  5. 2019Making Better Mistakes: Leveraging Class Hierarchies with Deep Networkscited by 113
  6. 2013Evaluation Measures for Hierarchical Classification: a unified view and novel approachescited by 46
  7. 2024What is YOLOv8: An In-Depth Exploration of the Internal Features of the Next-Generation Object Detectorcited by 45
  8. 2017B-CNN: Branch Convolutional Neural Network for Hierarchical Classificationcited by 37
  9. 2018Tree-CNN: A Hierarchical Deep Convolutional Neural Network for Incremental Learningcited by 34
  10. 2022HiFuse: Hierarchical Multi-Scale Feature Fusion Network for Medical Image Classificationcited by 30
  11. 2024Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computationcited by 29
  12. 2022Skin Lesion Recognition with Class-Hierarchy Regularized Hyperbolic Embeddingscited by 19
9 more
  1. 2022Analysis and Comparison of Classification Metricscited by 16
  2. 2020Deep Hiearchical Multi-Label Classification Applied to Chest X-Ray Abnormality Taxonomiescited by 9
  3. 2020Hierarchical Classification of Pulmonary Lesions: A Large-Scale Radio-Pathomics Studycited by 8
  4. 2020Learn Class Hierarchy using Convolutional Neural Networkscited by 7
  5. 2023Hierarchical confusion matrix for classification performance evaluationcited by 6
  6. 2020Hierarchical Class-Based Curriculum Losscited by 5
  7. 2022A Novel Hierarchical-Classification-Block Based Convolutional Neural Network for Source Camera Model Identificationcited by 2
  8. 2024Hierarchical Object Detection and Recognition Framework for Practical Plant Disease Diagnosiscited by 1
  9. 2025HGO-YOLO: Advancing Anomaly Behavior Detection with Hierarchical Features and Lightweight Optimized Detectioncited by 1

Built on by

Not cited yet.