让YOLOv8学会理解物体间的层级关系，提升分类准确性。
hYOLO Model: Enhancing Object Classification with Hierarchical Context in YOLOv8
- 设计了新的分层架构与损失函数，支持层级分类
- 在两个不同层级分类体系上均显著优于传统方法
- 适合需要语义层次理解的视觉识别任务
当前卷积神经网络的分类方法多为扁平分类，仅关注图像中指定物体的识别。然而真实世界中的物体常具有天然的层级结构，捕捉物体间的关系有助于增强上下文理解，并控制错误严重程度。本文提出一种基于YOLO模型家族的端到端分层检测与分类模型，引入新颖的分层架构、改进的损失函数及适配层级特性的评估指标。该模型在相同数据集的两种不同层级分类体系上进行训练与评估：一种忽略物体间的视觉相似性，另一种考虑类间常见视觉特征。实验结果表明，所提方法有效建模了真实世界物体中固有的层级结构，而传统扁平分类算法往往忽略此特性。
原文摘要 · Abstract (English)
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.
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。