计算机科学
人工智能
卷积神经网络
模式识别(心理学)
遗传程序设计
特征(语言学)
特征选择
上下文图像分类
特征提取
树(集合论)
图像(数学)
机器学习
任务(项目管理)
构造(python库)
人工神经网络
特征学习
深度学习
遗传算法
选择(遗传算法)
任务分析
可视化
图层(电子)
图像处理
决策树
树形结构
特征检测(计算机视觉)
多标签分类
作者
Qinyu Wang,Ying Bi,Bing Xue,Mengjie Zhang
标识
DOI:10.1109/tevc.2026.3675672
摘要
Fine-grained image classification (FGIC) remains a challenging task due to subtle inter-class differences and significant intra-class variations, particularly under limited training data. While genetic programming (GP) offers promising adaptability, the performance of existing GP-based methods is limited due to the reliance on traditional image descriptors for feature extraction/learning. To address this limitation, this paper proposes CNNGP, i.e., a novel multi-tree GP approach that utilizes the rich representations of pre-trained convolutional neural networks (CNNs) for FGIC. In CNNGP’s multi-tree representation, two trees are used to explore multi-level feature maps from pre-trained CNNs to generate saliency masks that highlight informative regions, and one tree is used to integrate them to construct higher-level and more powerful features for classification. Experiments on four commonly used FGIC datasets demonstrate that CNNGP can achieve superior (or at least competitive) performance to popular deep neural network methods and the recent GP-based method. Further analysis verifies the benefit of using dual saliency trees and visualizes how CNNGP captures complementary visual patterns that enhance feature learning. It also examines convolutional layer selection to reveal dataset-specific feature usage, demonstrating CNNGP’s adaptive feature learning capability.
科研通智能强力驱动
Strongly Powered by AbleSci AI