scholarly journals Improving Model Accuracy for Imbalanced Image Classification Tasks by Adding a Final Batch Normalization Layer: An Empirical Study

2021 ◽  
Author(s):  
Veysel Kocaman ◽  
Ofer M. Shir ◽  
Thomas Back
Keyword(s):  
Empirical Study ◽  
Image Classification ◽  
Model Accuracy ◽  
Batch Normalization ◽  
Classification Tasks ◽  
Final Batch

scholarly journals Instance Enhancement Batch Normalization: An Adaptive Regulator of Batch Noise

2020 ◽  
Vol 34 (04) ◽  
pp. 4819-4827
Author(s):  
Senwei Liang ◽  
Zhongzhan Huang ◽  
Mingfu Liang ◽  
Haizhao Yang
Keyword(s):  
Input Image ◽  
Point Of View ◽  
Specific Information ◽  
Network Training ◽  
Batch Normalization ◽  
Benchmark Datasets ◽  
Classification Tasks ◽  
Adaptive Regulator ◽  
Batch Noise ◽  
Parameter Increment

Batch Normalization (BN) (Ioffe and Szegedy 2015) normalizes the features of an input image via statistics of a batch of images and hence BN will bring the noise to the gradient of training loss. Previous works indicate that the noise is important for the optimization and generalization of deep neural networks, but too much noise will harm the performance of networks. In our paper, we offer a new point of view that the self-attention mechanism can help to regulate the noise by enhancing instance-specific information to obtain a better regularization effect. Therefore, we propose an attention-based BN called Instance Enhancement Batch Normalization (IEBN) that recalibrates the information of each channel by a simple linear transformation. IEBN has a good capacity of regulating the batch noise and stabilizing network training to improve generalization even in the presence of two kinds of noise attacks during training. Finally, IEBN outperforms BN with only a light parameter increment in image classification tasks under different network structures and benchmark datasets.

scholarly journals Label Rectification Learning through Kernel Extreme Learning Machine

2021 ◽  
Vol 2021 ◽  
pp. 1-6
Author(s):  
Qiang Cai ◽  
Fenghai Li ◽  
Yifan Chen ◽  
Haisheng Li ◽  
Jian Cao ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Image Classification ◽  
Extreme Learning Machine ◽  
Classification Performance ◽  
Considerable Progress ◽  
Strong Representation ◽  
Kernel Extreme Learning Machine ◽  
Classification Tasks ◽  
Learning Machine

Along with the strong representation of the convolutional neural network (CNN), image classification tasks have achieved considerable progress. However, majority of works focus on designing complicated and redundant architectures for extracting informative features to improve classification performance. In this study, we concentrate on rectifying the incomplete outputs of CNN. To be concrete, we propose an innovative image classification method based on Label Rectification Learning (LRL) through kernel extreme learning machine (KELM). It mainly consists of two steps: (1) preclassification, extracting incomplete labels through a pretrained CNN, and (2) label rectification, rectifying the generated incomplete labels by the KELM to obtain the rectified labels. Experiments conducted on publicly available datasets demonstrate the effectiveness of our method. Notably, our method is extensible which can be easily integrated with off-the-shelf networks for improving performance.

scholarly journals Applying LCS To Affective Image Classification In Spatial-Frequency Domain

2014 ◽  
Vol 4 (2) ◽  
pp. 99-123 ◽  
Author(s):  
Po-Ming Lee ◽  
Tzu-Chien Hsiao
Keyword(s):  
Pattern Recognition ◽  
Spatial Frequency ◽  
Image Classification ◽  
Frequency Domain ◽  
Model Building ◽  
Experimental Paradigm ◽  
Wide Range ◽  
Classification Tasks ◽  
Affective Image Classification ◽  
Spatial Frequency Domain

Abstract Recent studies have utilizes color, texture, and composition information of images to achieve affective image classification. However, the features related to spatial-frequency domain that were proven to be useful for traditional pattern recognition have not been tested in this field yet. Furthermore, the experiments conducted by previous studies are not internationally-comparable due to the experimental paradigm adopted. In addition, contributed by recent advances in methodology, that are, Hilbert-Huang Transform (HHT) (i.e. Empirical Mode Decomposition (EMD) and Hilbert Transform (HT)), the resolution of frequency analysis has been improved. Hence, the goal of this research is to achieve the affective image-classification task by adopting a standard experimental paradigm introduces by psychologists in order to produce international-comparable and reproducible results; and also to explore the affective hidden patterns of images in the spatial-frequency domain. To accomplish these goals, multiple human-subject experiments were conducted in laboratory. Extended Classifier Systems (XCSs) was used for model building because the XCS has been applied to a wide range of classification tasks and proved to be competitive in pattern recognition. To exploit the information in the spatial-frequency domain, the traditional EMD has been extended to a two-dimensional version. To summarize, the model built by using the XCS achieves Area Under Curve (AUC) = 0.91 and accuracy rate over 86%. The result of the XCS was compared with other traditional machine-learning algorithms (e.g., Radial-Basis Function Network (RBF Network)) that are normally used for classification tasks. Contributed by proper selection of features for model building, user-independent findings were obtained. For example, it is found that the horizontal visual stimulations contribute more to the emotion elicitation than the vertical visual stimulation. The effect of hue, saturation, and brightness; is also presented.

scholarly journals RSI-CB: A Large-Scale Remote Sensing Image Classification Benchmark Using Crowdsourced Data

Sensors ◽  
2020 ◽  
Vol 20 (6) ◽  
pp. 1594
Author(s):  
Haifeng Li ◽  
Xin Dou ◽  
Chao Tao ◽  
Zhixiang Wu ◽  
Jie Chen ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Image Classification ◽  
Large Scale ◽  
Remote Sensing Image ◽  
National Standard ◽  
Natural Image ◽  
Deep Convolutional Neural Networks ◽  
Remote Sensing Image Classification ◽  
Crowdsourced Data ◽  
Classification Tasks

Image classification is a fundamental task in remote sensing image processing. In recent years, deep convolutional neural networks (DCNNs) have experienced significant breakthroughs in natural image recognition. The remote sensing field, however, is still lacking a large-scale benchmark similar to ImageNet. In this paper, we propose a remote sensing image classification benchmark (RSI-CB) based on massive, scalable, and diverse crowdsourced data. Using crowdsourced data, such as Open Street Map (OSM) data, ground objects in remote sensing images can be annotated effectively using points of interest, vector data from OSM, or other crowdsourced data. These annotated images can, then, be used in remote sensing image classification tasks. Based on this method, we construct a worldwide large-scale benchmark for remote sensing image classification. This benchmark has large-scale geographical distribution and large total image number. It contains six categories with 35 sub-classes of more than 24,000 images of size 256 × 256 pixels. This classification system of ground objects is defined according to the national standard of land-use classification in China and is inspired by the hierarchy mechanism of ImageNet. Finally, we conduct numerous experiments to compare RSI-CB with the SAT-4, SAT-6, and UC-Merced data sets. The experiments show that RSI-CB is more suitable as a benchmark for remote sensing image classification tasks than other benchmarks in the big data era and has many potential applications.

scholarly journals Optical Compute Engine Using Deep CNN

2018 ◽  
Vol 7 (2.24) ◽  
pp. 541
Author(s):  
Zainab Zaveri ◽  
Dhruv Gosain ◽  
Arul Prakash M
Keyword(s):  
Neural Networks ◽  
Error Correction ◽  
Image Classification ◽  
Layered Structure ◽  
Data Sets ◽  
Complex Data ◽  
Complex Data Sets ◽  
Deep Cnn ◽  
Classification Tasks ◽  
Hierarchical Manner

We present an optical compute engine with implementation of Deep CNNs. CNNs are designed in an organized and hierarchical manner and their convolutional layers, subsampling layers alternate with each other, thus   the intricacy of the data per layer escalates as we traverse in the layered structure, which gives us more efficient results when dealing with complex data sets and computations. CNNs are realised in a distinctive way and vary from other neural networks in how their convolutional and subsampling layers are organised. DCNNs bring us very proficient results when it comes to image classification tasks. Recently, we have understood that generalization is more important when compared to the neural network’s depth for more optimised image classification. Our feature extractors are learned in an unsupervised way, hence the results get more precise after every backpropagation and error correction.

Sign in / Sign up

Export Citation Format

Share Document