scholarly journals Multidimensional Face Representation in a Deep Convolutional Neural Network Reveals the Mechanism Underlying AI Racism

2021 ◽  
Vol 15 ◽  
Author(s):  
Jinhua Tian ◽  
Hailun Xie ◽  
Siyuan Hu ◽  
Jia Liu
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Underlying Mechanism ◽  
Deep Convolutional Neural Network ◽  
The Other ◽  
Training Data ◽  
Identification Accuracy ◽  
Social Bias ◽  
Novel Approach ◽  
Ai Ethics

The increasingly popular application of AI runs the risk of amplifying social bias, such as classifying non-white faces as animals. Recent research has largely attributed this bias to the training data implemented. However, the underlying mechanism is poorly understood; therefore, strategies to rectify the bias are unresolved. Here, we examined a typical deep convolutional neural network (DCNN), VGG-Face, which was trained with a face dataset consisting of more white faces than black and Asian faces. The transfer learning result showed significantly better performance in identifying white faces, similar to the well-known social bias in humans, the other-race effect (ORE). To test whether the effect resulted from the imbalance of face images, we retrained the VGG-Face with a dataset containing more Asian faces, and found a reverse ORE that the newly-trained VGG-Face preferred Asian faces over white faces in identification accuracy. Additionally, when the number of Asian faces and white faces were matched in the dataset, the DCNN did not show any bias. To further examine how imbalanced image input led to the ORE, we performed a representational similarity analysis on VGG-Face's activation. We found that when the dataset contained more white faces, the representation of white faces was more distinct, indexed by smaller in-group similarity and larger representational Euclidean distance. That is, white faces were scattered more sparsely in the representational face space of the VGG-Face than the other faces. Importantly, the distinctiveness of faces was positively correlated with identification accuracy, which explained the ORE observed in the VGG-Face. In summary, our study revealed the mechanism underlying the ORE in DCNNs, which provides a novel approach to studying AI ethics. In addition, the face multidimensional representation theory discovered in humans was also applicable to DCNNs, advocating for future studies to apply more cognitive theories to understand DCNNs' behavior.

scholarly journals Multidimensional face representation in deep convolutional neural network reveals the mechanism underlying AI racism

2020 ◽  
Author(s):  
Jinhua Tian ◽  
Hailun Xie ◽  
Siyuan Hu ◽  
Jia Liu
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Underlying Mechanism ◽  
Deep Convolutional Neural Network ◽  
The Other ◽  
Identification Accuracy ◽  
Social Bias ◽  
Novel Approach ◽  
The Face ◽  
Ai Ethics

AbstractThe increasingly popular application of AI runs the risks of amplifying social bias, such as classifying non-white faces to animals. Recent research has attributed the bias largely to data for training. However, the underlying mechanism is little known, and therefore strategies to rectify the bias are unresolved. Here we examined a typical deep convolutional neural network (DCNN), VGG-Face, which was trained with a face dataset consisting of more white faces than black and Asian faces. The transfer learning result showed significantly better performance in identifying white faces, just like the well-known social bias in human, the other-race effect (ORE). To test whether the effect resulted from the imbalance of face images, we retrained the VGG-Face with a dataset containing more Asian faces, and found a reverse ORE that the newly-trained VGG-Face preferred Asian faces over white faces in identification accuracy. In addition, when the number of Asian faces and white faces were matched in the dataset, the DCNN did not show any bias. To further examine how imbalanced image input led to the ORE, we performed the representational similarity analysis on VGG-Face’s activation. We found that when the dataset contained more white faces, the representation of white faces was more distinct, indexed by smaller ingroup similarity and larger representational Euclidean distance. That is, white faces were scattered more sparsely in the representational face space of the VGG-Face than the other faces. Importantly, the distinctiveness of faces was positively correlated with the identification accuracy, which explained the ORE observed in the VGG-Face. In sum, our study revealed the mechanism underlying the ORE in DCNNs, which provides a novel approach of study AI ethics. In addition, the face multidimensional representation theory discovered in human was found also applicable to DCNNs, advocating future studies to apply more cognitive theories to understand DCNN’s behavior.

scholarly journals Comparing performance of deep convolutional neural network with orthopaedic surgeons on identification of total hip prosthesis design from plain radiographs

2020 ◽  
Author(s):  
Alireza Borjali ◽  
Antonia F. Chen ◽  
Hany S. Bedair ◽  
Christopher M. Melnic ◽  
Orhun K. Muratoglu ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Deep Convolutional Neural Network ◽  
Training Data ◽  
Identification Accuracy ◽  
Automated System ◽  
Implant Design ◽  
Plain Radiographs ◽  
Orthopaedic Surgeons ◽  
Total Hip

ABSTRACTA crucial step in preoperative planning for a revision total hip replacement (THR) surgery is accurate identification of failed implant design, especially if one or more well-fixed/functioning components are to be retained. Manual identification of the implant design from preoperative radiographic images can be time-consuming and inaccurate, which can ultimately lead to increased operating room time, more complex surgery, and increased healthcare costs. No automated system has been developed to accurately and efficiently identify THR implant designs. In this study, we present a novel, fully automatic and interpretable approach to identify the design of nine different THR femoral implants from plain radiographs using deep convolutional neural network (CNN). We also compared the CNN’s performance with three board-certified and fellowship trained orthopaedic surgeons. The CNN achieved on-par accuracy with the orthopaedic surgeons while being significantly faster. The need for additional training data for less distinct designs was also highlighted. Such CNN can be used to automatically identify the design of a failed THR femoral implant preoperatively in just a fraction of a second, saving time and improving identification accuracy.

scholarly journals Object Detection in Ground-Penetrating Radar Images Using a Deep Convolutional Neural Network and Image Set Preparation by Migration

2018 ◽  
Vol 2018 ◽  
pp. 1-8 ◽  
Author(s):  
Kazuya Ishitsuka ◽  
Shinichiro Iso ◽  
Kyosuke Onishi ◽  
Toshifumi Matsuoka
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Ground Penetrating Radar ◽  
Deep Convolutional Neural Network ◽  
Training Data ◽  
Neural Network Approach ◽  
Radar Images ◽  
Image Set ◽  
Ground Penetrating ◽  
Better Than

Ground-penetrating radar allows the acquisition of many images for investigation of the pavement interior and shallow geological structures. Accordingly, an efficient methodology of detecting objects, such as pipes, reinforcing steel bars, and internal voids, in ground-penetrating radar images is an emerging technology. In this paper, we propose using a deep convolutional neural network to detect characteristic hyperbolic signatures from embedded objects. As a first step, we developed a migration-based method to collect many training data and created 53510 categorized images. We then examined the accuracy of the deep convolutional neural network in detecting the signatures. The accuracy of the classification was 0.945 (94.5%)–0.979 (97.9%) when using several thousands of training images and was much better than the accuracy of the conventional neural network approach. Our results demonstrate the effectiveness of the deep convolutional neural network in detecting characteristic events in ground-penetrating radar images.

CT Image Segmentation of Liver Tumor with Deep Convolutional Neural Network

2021 ◽  
Vol 11 (2) ◽  
pp. 337-344
Author(s):  
Yao Zeng ◽  
Huanhuan Dai
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Automatic Segmentation ◽  
Abdominal Cavity ◽  
Mutual Exclusion ◽  
Image Data ◽  
Deep Convolutional Neural Network ◽  
Training Data ◽  
Segmentation Method ◽  
Segmentation Boundary

The liver is the largest substantial organ in the abdominal cavity of the human body. Its structure is complex, the incidence of vascular abundance is high, and it has been seriously ribbed, human health and life. In this study, an automatic segmentation method based on deep convolutional neural network is proposed. Image data blocks of different sizes are extracted as training data and different network structures are designed, and features are automatically learned to obtain a segmentation structure of the tumor. Secondly, in order to further refine the segmentation boundary, we establish a multi-region segmentation model with region mutual exclusion constraints. The model combines the image grayscale, gradient and prior probability information, and overcomes the problem that the boundary point attribution area caused by boundary blur and regional adhesion is difficult to determine. Finally, the model is solved quickly using the time-invisible multi-phase level set. Compared with the traditional multi-organ segmentation method, this method does not require registration or model initialization. The experimental results show that the model can segment the liver, kidney and spleen quickly and effectively, and the segmentation accuracy reaches the advanced level of current methods.

scholarly journals The Effect of Different Flaw Data to Machine Learning Powered Ultrasonic Inspection

2021 ◽  
Vol 40 (1) ◽  
Author(s):  
Tuomas Koskinen ◽  
Iikka Virkkunen ◽  
Oskar Siljama ◽  
Oskari Jessen-Juhler
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Convolutional Neural Network ◽  
Image Recognition ◽  
Phased Array ◽  
Ultrasonic Inspection ◽  
Deep Convolutional Neural Network ◽  
Flaw Size ◽  
Training Data ◽  
Link Type

AbstractPrevious research (Li et al., Understanding the disharmony between dropout and batch normalization by variance shift. CoRR abs/1801.05134 (2018). http://arxiv.org/abs/1801.05134arXiv:1801.05134) has shown the plausibility of using a modern deep convolutional neural network to detect flaws from phased-array ultrasonic data. This brings the repeatability and effectiveness of automated systems to complex ultrasonic signal evaluation, previously done exclusively by human inspectors. The major breakthrough was to use virtual flaws to generate ample flaw data for the teaching of the algorithm. This enabled the use of raw ultrasonic scan data for detection and to leverage some of the approaches used in machine learning for image recognition. Unlike traditional image recognition, training data for ultrasonic inspection is scarce. While virtual flaws allow us to broaden the data considerably, original flaws with proper flaw-size distribution are still required. This is of course the same for training human inspectors. The training of human inspectors is usually done with easily manufacturable flaws such as side-drilled holes and EDM notches. While the difference between these easily manufactured artificial flaws and real flaws is obvious, human inspectors still manage to train with them and perform well in real inspection scenarios. In the present work, we use a modern, deep convolutional neural network to detect flaws from phased-array ultrasonic data and compare the results achieved from different training data obtained from various artificial flaws. The model demonstrated good generalization capability toward flaw sizes larger than the original training data, and the effect of the minimum flaw size in the data set affects the $$a_{90/95}$$ a 90 / 95 value. This work also demonstrates how different artificial flaws, solidification cracks, EDM notch and simple simulated flaws generalize differently.

scholarly journals Semantic Segmentation of Urban Buildings from VHR Remote Sensing Imagery Using a Deep Convolutional Neural Network

2019 ◽  
Vol 11 (15) ◽  
pp. 1774 ◽  
Author(s):  
Yaning Yi ◽  
Zhijie Zhang ◽  
Wanchang Zhang ◽  
Chuanrong Zhang ◽  
Weidong Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Convolutional Neural Network ◽  
Semantic Segmentation ◽  
Deep Convolutional Neural Network ◽  
The Other ◽  
Feature Maps ◽  
Remote Sensing Imagery ◽  
Urban Buildings ◽  
Sampling Network

Urban building segmentation is a prevalent research domain for very high resolution (VHR) remote sensing; however, various appearances and complicated background of VHR remote sensing imagery make accurate semantic segmentation of urban buildings a challenge in relevant applications. Following the basic architecture of U-Net, an end-to-end deep convolutional neural network (denoted as DeepResUnet) was proposed, which can effectively perform urban building segmentation at pixel scale from VHR imagery and generate accurate segmentation results. The method contains two sub-networks: One is a cascade down-sampling network for extracting feature maps of buildings from the VHR image, and the other is an up-sampling network for reconstructing those extracted feature maps back to the same size of the input VHR image. The deep residual learning approach was adopted to facilitate training in order to alleviate the degradation problem that often occurred in the model training process. The proposed DeepResUnet was tested with aerial images with a spatial resolution of 0.075 m and was compared in performance under the exact same conditions with six other state-of-the-art networks—FCN-8s, SegNet, DeconvNet, U-Net, ResUNet and DeepUNet. Results of extensive experiments indicated that the proposed DeepResUnet outperformed the other six existing networks in semantic segmentation of urban buildings in terms of visual and quantitative evaluation, especially in labeling irregular-shape and small-size buildings with higher accuracy and entirety. Compared with the U-Net, the F1 score, Kappa coefficient and overall accuracy of DeepResUnet were improved by 3.52%, 4.67% and 1.72%, respectively. Moreover, the proposed DeepResUnet required much fewer parameters than the U-Net, highlighting its significant improvement among U-Net applications. Nevertheless, the inference time of DeepResUnet is slightly longer than that of the U-Net, which is subject to further improvement.

Sign in / Sign up

Export Citation Format

Share Document