Automatically designing CNN architectures using genetic algorithm for image classification

Abstract

Convolutional Neural Networks (CNNs) have gained a remarkable success on many image classification tasks in recent years. However, the performance of CNNs highly relies upon their architectures. For most state-of-the-art CNNs, their architectures are often manually-designed with expertise in both CNNs and the investigated problems. Therefore, it is difficult for users, who have no extended expertise in CNNs, to design optimal CNN architectures for their own image classification problems of interest. In this paper, we propose an automatic CNN architecture design method by using genetic algorithms, to effectively address the image classification tasks. The most merit of the proposed algorithm remains in its "automatic" characteristic that users do not need domain knowledge of CNNs when using the proposed algorithm, while they can still obtain a promising CNN architecture for the given images. The proposed algorithm is validated on widely used benchmark image classification datasets, by comparing to the state-of-the-art peer competitors covering eight manually-designed CNNs, seven automatic+manually tuning and five automatic CNN architecture design algorithms. The experimental results indicate the proposed algorithm outperforms the existing automatic CNN architecture design algorithms in terms of classification accuracy, parameter numbers and consumed computational resources. The proposed algorithm also shows the very comparable classification accuracy to the best one from manually-designed and automatic+manually tuning CNNs, while consumes much less of computational resource.

References in corpus (17)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Sequence to Sequence Learning with Neural Networks
• TensorFlow: A system for large-scale machine learning
• Neural Architecture Search with Reinforcement Learning
• Improved Regularization of Convolutional Neural Networks with Cutout
• Striving for Simplicity: The All Convolutional Net
• DARTS: Differentiable Architecture Search
• Training Very Deep Networks
• Highway Networks
• Large-Scale Evolution of Image Classifiers
• IGD Indicator-based Evolutionary Algorithm for Many-objective Optimization Problems
• Transfer Learning based Dynamic Multiobjective Optimization Algorithms
• Designing Neural Network Architectures using Reinforcement Learning
• Efficient Architecture Search by Network Transformation
• Skip Connections Eliminate Singularities
• Evolving Deep Convolutional Neural Networks for Image Classification
• Improved Regularity Model-based EDA for Many-objective Optimization

Cited by in corpus (30)

• A Survey on Evolutionary Neural Architecture Search
• Real-Time COVID-19 Diagnosis from X-Ray Images Using Deep CNN and Extreme Learning Machines Stabilized by Chimp Optimization Algorithm
• A Survey on Evolutionary Computation for Computer Vision and Image Analysis: Past, Present, and Future Trends
• Source Aware Deep Learning Framework for Hand Kinematic Reconstruction using EEG Signal
• Evolving Deep Convolutional Neural Network by Hybrid Sine-Cosine and Extreme Learning Machine for Real-time COVID19 Diagnosis from X-Ray Images
• Fast and Accurate Road Crack Detection Based on Adaptive Cost-Sensitive Loss Function
• Application of artificial intelligence techniques for automated detection of myocardial infarction: A review
• NASCaps: A Framework for Neural Architecture Search to Optimize the Accuracy and Hardware Efficiency of Convolutional Capsule Networks
• Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methods
• Rethinking Co-design of Neural Architectures and Hardware Accelerators
• Multi-Objective Evolutionary Design of Deep Convolutional Neural Networks for Image Classification
• HALF: Holistic Auto Machine Learning for FPGAs
• Apollo: Transferable Architecture Exploration
• From Federated Learning to Federated Neural Architecture Search: A Survey
• Self-supervised Representation Learning for Evolutionary Neural Architecture Search
• Evolution under Length Constraints for CNN Architecture design
• A Deep Neural Networks ensemble workflow from hyperparameter search to inference leveraging GPU clusters
• A New Compensatory Genetic Algorithm-Based Method for Effective Compressed Multi-function Convolutional Neural Network Model Selection with Multi-Objective Optimization
• CDE-GAN: Cooperative Dual Evolution Based Generative Adversarial Network
• Multi-Knowledge Fusion for New Feature Generation in Generalized Zero-Shot Learning
• Evolution-based Fine-tuning of CNNs for Prostate Cancer Detection
• Multi-Space Evolutionary Search for Large-Scale Optimization
• Data-Driven Offline Optimization For Architecting Hardware Accelerators
• PairNets: Novel Fast Shallow Artificial Neural Networks on Partitioned Subspaces
• Two Novel Performance Improvements for Evolving CNN Topologies
• Global2Local: Efficient Structure Search for Video Action Segmentation
• Multi-objective Evolutionary Approach for Efficient Kernel Size and Shape for CNN
• EZCrop: Energy-Zoned Channels for Robust Output Pruning
• ConAM: Confidence Attention Module for Convolutional Neural Networks
• BNAS-v2: Memory-efficient and Performance-collapse-prevented Broad Neural Architecture Search