Image classification method on class imbalance datasets using multi-scale CNN and two-stage transfer learning

2021 ◽  
Author(s):  
Jiahuan Liu ◽  
Fei Guo ◽  
Huang Gao ◽  
Zhigao Huang ◽  
Yun Zhang ◽  
...  
Keyword(s):  
Image Classification ◽  
Transfer Learning ◽  
Class Imbalance ◽  
Classification Method ◽  
Two Stage ◽  
Multi Scale

scholarly journals Cloud Image Classification Method Based on Deep Convolutional Neural Network

2020 ◽  
Vol 38 (4) ◽  
pp. 740-746
Author(s):  
Fei Zhang ◽  
Jie Yan
Keyword(s):  
Image Classification ◽  
Transfer Learning ◽  
Training Model ◽  
Classification Method ◽  
Support Vector ◽  
Test Accuracy ◽  
Learning Technology ◽  
Deep Convolutional Neural Networks ◽  
Fitting In ◽  
The Cost

Compared with satellite remote sensing images, ground-based invisible images have limited swath, but featured in higher resolution, more distinct cloud features, and the cost is greatly reduced, conductive to continuous meteorological observation of local areas. For the first time, this paper proposed a high-resolution cloud image classification method based on deep learning and transfer learning technology for ground-based invisible images. Due to the limited amount of samples, traditional classifiers such as support vector machine can't effectively extract the unique features of different types of clouds, and directly training deep convolutional neural networks leads to over-fitting. In order to prevent the network from over-fitting, this paper proposed applying transfer learning method to fine-tune the pre-training model. The proposed network achieved as high as 85.19% test accuracy on 6-type cloud images classification task. The networks proposed in this paper can be applied to classify digital photos captured by cameras directly, which will reduce the cost of system greatly.

scholarly journals Gated Convolutional Networks with Hybrid Connectivity for Image Classification

2020 ◽  
Vol 34 (07) ◽  
pp. 12581-12588
Author(s):  
Chuanguang Yang ◽  
Zhulin An ◽  
Hui Zhu ◽  
Xiaolong Hu ◽  
Kun Zhang ◽  
...  
Keyword(s):  
Image Classification ◽  
State Of The Art ◽  
Experimental Results ◽  
Two Stage ◽  
Convolutional Networks ◽  
Multi Scale ◽  
Simple Addition

We propose a simple yet effective method to reduce the redundancy of DenseNet by substantially decreasing the number of stacked modules by replacing the original bottleneck by our SMG module, which is augmented by local residual. Furthermore, SMG module is equipped with an efficient two-stage pipeline, which aims to DenseNet-like architectures that need to integrate all previous outputs, i.e., squeezing the incoming informative but redundant features gradually by hierarchical convolutions as a hourglass shape and then exciting it by multi-kernel depthwise convolutions, the output of which would be compact and hold more informative multi-scale features. We further develop a forget and an update gate by introducing the popular attention modules to implement the effective fusion instead of a simple addition between reused and new features. Due to the Hybrid Connectivity (nested combination of global dense and local residual) and Gated mechanisms, we called our network as the HCGNet. Experimental results on CIFAR and ImageNet datasets show that HCGNet is more prominently efficient than DenseNet, and can also significantly outperform state-of-the-art networks with less complexity. Moreover, HCGNet also shows the remarkable interpretability and robustness by network dissection and adversarial defense, respectively. On MS-COCO, HCGNet can consistently learn better features than popular backbones.

scholarly journals A Multi-Domain Collaborative Transfer Learning Method with Multi-Scale Repeated Attention Mechanism for Underwater Side-Scan Sonar Image Classification

2022 ◽  
Vol 14 (2) ◽  
pp. 355
Author(s):  
Zhen Cheng ◽  
Guanying Huo ◽  
Haisen Li
Keyword(s):  
Feature Extraction ◽  
Deep Learning ◽  
Image Classification ◽  
Transfer Learning ◽  
Fine Tuning ◽  
Side Scan Sonar ◽  
Multi Scale ◽  
Sonar Image ◽  
Optical Images

Due to the strong speckle noise caused by the seabed reverberation which makes it difficult to extract discriminating and noiseless features of a target, recognition and classification of underwater targets using side-scan sonar (SSS) images is a big challenge. Moreover, unlike classification of optical images which can use a large dataset to train the classifier, classification of SSS images usually has to exploit a very small dataset for training, which may cause classifier overfitting. Compared with traditional feature extraction methods using descriptors—such as Haar, SIFT, and LBP—deep learning-based methods are more powerful in capturing discriminating features. After training on a large optical dataset, e.g., ImageNet, direct fine-tuning method brings improvement to the sonar image classification using a small-size SSS image dataset. However, due to the different statistical characteristics between optical images and sonar images, transfer learning methods—e.g., fine-tuning—lack cross-domain adaptability, and therefore cannot achieve very satisfactory results. In this paper, a multi-domain collaborative transfer learning (MDCTL) method with multi-scale repeated attention mechanism (MSRAM) is proposed for improving the accuracy of underwater sonar image classification. In the MDCTL method, low-level characteristic similarity between SSS images and synthetic aperture radar (SAR) images, and high-level representation similarity between SSS images and optical images are used together to enhance the feature extraction ability of the deep learning model. Using different characteristics of multi-domain data to efficiently capture useful features for the sonar image classification, MDCTL offers a new way for transfer learning. MSRAM is used to effectively combine multi-scale features to make the proposed model pay more attention to the shape details of the target excluding the noise. Experimental results of classification show that, in using multi-domain data sets, the proposed method is more stable with an overall accuracy of 99.21%, bringing an improvement of 4.54% compared with the fine-tuned VGG19. Results given by diverse visualization methods also demonstrate that the method is more powerful in feature representation by using the MDCTL and MSRAM.

Sign in / Sign up

Export Citation Format

Share Document