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. While transferring the learned knowledge from one task to another, fine-tuning with the target-dependent fully connected layers produces better results over the target task. In this paper, the proposed AutoFCL model attempts to learn the structure of Fully Connected (FC) layers of a CNN automatically using Bayesian optimization. To evaluate the performance of the proposed AutoFCL, we utilize five popular 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广受欢迎的机器学习模型,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性。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性。然而,为某项任务设计最先进的CNN仍然是一项非边际和具有挑战性的任务。在将学到的知识从一个任务转移到另一个任务的同时,与完全依赖目标的层进行微调,在目标任务上产生更好的结果。在本文中,AutoFCL模型试图利用Bayesian优化来学习CNN自动的完全连通层(FC)的准确性结构。为了评估拟议的AutoFCL的性能,我们使用了五种受欢迎的CNN模型,如VGG-16、ResNet、DesenseNet、MolvetNet和NASNetMobile。在三个基准数据集上进行了实验,即Caltech-101、Ox-102 flowers和UC Mercland use数据集。精细化新学的完全精确性(目标) 101) 和FC-C-Cchde-Lde-lax-lax-lax-lax-lax-lax-lax-lax-lax-mod-rod-rod-mod-mod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rod-rods-mocs-mocs-mocs-rod-mods-mod-mod-mod-rod-rod-rod-mod-mod-mod-mod-mod-mod-rod-mod-rod-rod-lax-lax-lax-lax-ro