Data-efficient image classification is a challenging task that aims to solve image classification using small training data. Neural network-based deep learning methods are effective for image classification, but they typically require large-scale training data and have major limitations such as requiring expertise to design network architectures and having poor interpretability. Evolutionary deep learning is a recent hot topic that combines evolutionary computation with deep learning. However, most evolutionary deep learning methods focus on evolving architectures of neural networks, which still suffer from limitations such as poor interpretability. To address this, this paper proposes a new genetic programming-based evolutionary deep learning approach to data-efficient image classification. The new approach can automatically evolve variable-length models using many important operators from both image and classification domains. It can learn different types of image features from colour or gray-scale images, and construct effective and diverse ensembles for image classification. A flexible multi-layer representation enables the new approach to automatically construct shallow or deep models/trees for different tasks and perform effective transformations on the input data via multiple internal nodes. The new approach is applied to solve five image classification tasks with different training set sizes. The results show that it achieves better performance in most cases than deep learning methods for data-efficient image classification. A deep analysis shows that the new approach has good convergence and evolves models with high interpretability, different lengths/sizes/shapes, and good transferability.
翻译:以神经网络为基础的深层次学习方法对图像分类有效,但它们通常需要大规模培训数据,而且具有重大局限性,例如需要设计网络结构的专门知识,而且解释性差。进化深层次学习是最近一个热题,将进化计算与深层次学习结合起来。然而,大多数深层次的深层次学习方法侧重于神经网络的演变结构,这些结构仍然受到诸如解释性差等限制。为了解决这个问题,本文件提议采用基于基因的基于编程的深层次深层次学习方法来进行数据高效的图像分类。新的方法可以自动地利用来自图像和分类领域的许多重要操作员来发展变长模型。它可以从彩色或灰度图像中学习不同类型的图像特征,并且为图像分类建立有效和多样的组合。灵活的多层次教学方法有助于通过多种内部节点,自动地为不同的任务构建浅度或深层的模型/树枝,并对输入数据进行有效的转换。新的方法应用于以不同的培训尺寸大小解决五种图像分类任务。新的方法可以自动演变变长模型。结果显示,在高层次的趋同性分析中,在高层次的模型中可以取得比高层次分析。