Genetic Programming-Based Evolutionary Deep Learning for Data-Efficient Image Classification

@article{Bi2022GeneticPE,
  title={Genetic Programming-Based Evolutionary Deep Learning for Data-Efficient Image Classification},
  author={Ying Bi and Bing Xue and Mengjie Zhang},
  journal={ArXiv},
  year={2022},
  volume={abs/2209.13233}
}
—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… 

References

SHOWING 1-10 OF 66 REFERENCES

An Evolutionary Deep Learning Approach Using Genetic Programming with Convolution Operators for Image Classification

This paper proposed a new GP-based EDL method with convolution operators (COGP) for feature learning on binary and multi-class image classification and demonstrated that COGP achieved significantly better performance in most comparisons with 11 effectively competitive methods.

Genetic Programming With a New Representation to Automatically Learn Features and Evolve Ensembles for Image Classification

An evolutionary approach based on genetic programming to automatically and simultaneously learn informative features and evolve effective ensembles for image classification is proposed and achieves better classification accuracy on most datasets than the competitive methods.

Evolving Deep Convolutional Neural Networks for Image Classification

A new method using genetic algorithms for evolving the architectures and connection weight initialization values of a deep convolutional neural network to address image classification problems and a novel fitness evaluation method is proposed to speed up the heuristic search with substantially less computational resource.

Dual-Tree Genetic Programming for Few-Shot Image Classification

A GP-based approach with a dual-tree representation and a new fitness function to automatically learn image features for FSIC achieves significantly better performance than a large number of state-of-the-art methods on nine 3-shot and 5-shot image classification datasets.

Learning and Sharing: A Multitask Genetic Programming Approach to Image Feature Learning

A new knowledge sharing mechanism based on a new individual representation is developed to allow GP to automatically learn what to share across two tasks and to improve its learning performance.

Structurally Layered Representation Learning: Towards Deep Learning Through Genetic Programming

A structurally layered GP formulation is introduced, together with an efficient scheme to explore the search space and it is shown that this framework can be used to learn representations from large data sets of high dimensional raw data.

Feature Learning for Image Classification Via Multiobjective Genetic Programming

Experimental results verify that the proposed evolutionary learning methodology significantly outperforms many state-of-the-art hand-designed features and two feature learning techniques in terms of classification accuracy.

Binary Image Classification: A Genetic Programming Approach to the Problem of Limited Training Instances

The results show that one-shot GP and compound-GP outperform or achieve results comparable to competitor methods, and the features extracted by these two methods improve the performance of other classifiers with handcrafted features and those extracted by a recently developed GP-based method in most cases.

Multiobjective Evolutionary Design of Deep Convolutional Neural Networks for Image Classification

This work proposes an evolutionary algorithm for searching neural architectures under multiple objectives, such as classification performance and floating point operations (FLOPs), and addresses the first shortcoming by populating a set of architectures to approximate the entire Pareto frontier through genetic operations that recombine and modify architectural components progressively.

Deep Residual Learning for Image Recognition

This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
...