Deep Convolutional Neural Networks (CNN) have evolved as popular machine learning models for image classification during the past few years, due to their ability to learn the problem-specific features directly from the input images. The success of deep learning models solicits architecture engineering rather than hand-engineering the features. However, designing state-of-the-art CNN for a given task remains a non-trivial and challenging task, especially when training data size is less. To address this phenomenon, transfer learning has been used as a popularly adopted technique. While transferring the learned knowledge from one task to another, fine-tuning with the target-dependent Fully Connected (FC) layers generally produces better results over the target task. In this paper, the proposed AutoFCL model attempts to learn the structure of FC layers of a CNN automatically using Bayesian optimization. To evaluate the performance of the proposed AutoFCL, we utilize five pre-trained CNN models such as VGG-16, ResNet, DenseNet, MobileNet, and NASNetMobile. The experiments are conducted on three benchmark datasets, namely CalTech-101, Oxford-102 Flowers, and UC Merced Land Use datasets. Fine-tuning the newly learned (target-dependent) FC layers leads to state-of-the-art performance, according to the experiments carried out in this research. The proposed AutoFCL method outperforms the existing methods over CalTech-101 and Oxford-102 Flowers datasets by achieving the accuracy of 94:38% and 98:89%, respectively. However, our method achieves comparable performance on the UC Merced Land Use dataset with 96:83% accuracy.
翻译:深革命神经网络(CNN)在过去几年中演变为流行型机器学习模型,用于图像分类,在过去几年中,由于能够直接从输入图像中学习特定问题的特点,深层次学习模型的成功需要的是建筑工程,而不是手工设计这些特点。然而,为特定任务设计最先进的CNN仍然是一项非边际和具有挑战性的任务,特别是在培训数据规模较小的情况下。为解决这一现象,转移学习被作为一种普遍采用的技术。在将所学知识从一个任务转移到另一个任务时,与依赖目标的完全连通(FC)层进行微调通常会为目标任务带来更好的结果。在本论文中,拟议的AutoFCL模型试图利用Bayesian优化来学习CNN的FC层结构。为了评估拟议的AutoFCL的绩效,我们使用了五种经过预先训练的CNN模型,如VGG-16、ResNet、DenseNet、移动网络和NASNetMoberblementalMobile。在三个基准数据集上进行了实验,即CalT-C-C-Caltradeal-listrup the dal-rodud the dal-dal-ledal-lemental-learate Studate Studate Studate Studate State Studate Studutes resutes, lex the dal-lex the dal-lex the dal-lexed the dal-lemental-lemental-lemental-lemental-lemental-lemental-lemental-lection-lements-lection-lection-lementalddddddddd-lements-lements-lements-lements-lements-lements-lements-lementaldal-leddddddds-leddddddddaldalddddddaldaldaldaldaldaldald ledds-leddalddddd-lements)上,我们,在通过三种研究中,通过三种方法上,在最新数据方法上,通过三种方法实现了。在最新数据方法,在最新数据方法中实现了。