Filters








666 Hits in 5.3 sec

NewsBag: A Benchmark Multimodal Dataset for Fake News Detection

Sarthak Jindal, Raghav Sood, Richa Singh, Mayank Vatsa, Tanmoy Chakraborty
2020 AAAI Conference on Artificial Intelligence  
In the second dataset, we study the effect of data augmentation by using a Bag of Words approach to increase the quantity of fake news data.  ...  We propose two novel benchmark multimodal datasets, consisting of text and images, to enhance the quality of fake news detection.  ...  This encourages the use of deep learning models which can learn hidden or latent features in the data.  ... 
dblp:conf/aaai/JindalS0V020 fatcat:ajthnxda4zecdnqyj6dq6mvvxe

Random CapsNet Forest Model for Imbalanced Malware Type Classification Task [article]

Aykut Çayır, Uğur Ünal, Hasan Dağ
2020 arXiv   pre-print
However, traditional deep learning architectures and components cause very complex and data sensitive models.  ...  Many malware type classification models empowered by machine and deep learning achieve superior accuracies to predict malware types.Machine learning based models need to do heavy feature engineering and  ...  Acknowledgement This work is supported by The Scientific and Technological Research Council of Turkey under the grant number 118E400.  ... 
arXiv:1912.10836v4 fatcat:mvvxu2kmfnfkpoddet3ibewm3u

Encoding Retina Image to Words using Ensemble of Vision Transformers for Diabetic Retinopathy Grading

Nouar AlDahoul, Hezerul Abdul Karim, Myles Joshua Toledo Tan, Mhd Adel Momo, Jamie Ledesma Fermin
2021 F1000Research  
This dataset includes highly imbalanced data with five levels of severity: No DR, Mild, Moderate, Severe, and Proliferative DR.  ...  A challenging public DR dataset proposed in a 2015 Kaggle challenge was used for training and evaluation of the proposed method.  ...  Deep neural networks, such as CNNs, with much larger datasets have also been used for classification tasks in the diagnosis and grading of DR.  ... 
doi:10.12688/f1000research.73082.1 fatcat:d2mtsxrnkrfuflero42nrbfp7y

Feature Fusion for Efficient Object Classification Using Deep and Shallow Learning

T. Janani, A. Ramanan
2017 International Journal of Machine Learning and Computing  
Bag-of-Features (BoF) approach have been successfully applied to visual object classification tasks.  ...  The dimension of convolutional features were reduced using PCA technique and the bag-of-features representation was reduced by tailoring the visual codebook using a statistical codeword selection method  ...  Classification Using Deep and Shallow Learning T.  ... 
doi:10.18178/ijmlc.2017.7.5.633 fatcat:m7cotz7bkzcjrmk4jzmm6be7iq

Artificial Intelligence in Smart Farms: Plant Phenotyping for Species Recognition and Health Condition Identification Using Deep Learning

Anirban Jyoti Hati, Rajiv Ranjan Singh
2021 AI  
However, this work used an imbalanced dataset having an unequal number of images, applied data augmentation to increase accuracy, organised data as multiple test cases and classes, and, most importantly  ...  Among the contemporary works for species recognition (SR) and infection detection of plants, the majority of them have performed experiments on balanced datasets and used accuracy as the evaluation parameter  ...  S, Ramesh, Dean Research and Innovation, Presidency University, Itgalpur Raankunte, Yehalanka, Bengaluru, Karnataka 560064, India for all kinds of logistics and technical support.  ... 
doi:10.3390/ai2020017 fatcat:gzfpckhrmve3xkwrfnmznosg2e

Discriminative Sparse Neighbor Approximation for Imbalanced Learning [article]

Chen Huang, Chen Change Loy, Xiaoou Tang
2016 arXiv   pre-print
The proposed imbalanced learning method can be applied to both classification and regression tasks at a wide range of imbalance levels.  ...  These methods further deteriorate on small, imbalanced data that has a large degree of class overlap.  ...  Unfortunately strong biases are still observed on imbalanced datasets, and we provide here an explicit solution to imbalanced learning with better results, using no deep features.  ... 
arXiv:1602.01197v1 fatcat:fxnd22qzlnd5rdtxxzfuwk6pza

Deep Long-Tailed Learning: A Survey [article]

Yifan Zhang, Bingyi Kang, Bryan Hooi, Shuicheng Yan, Jiashi Feng
2021 arXiv   pre-print
In the last decade, deep learning has emerged as a powerful recognition model for learning high-quality image representations and has led to remarkable breakthroughs in generic visual recognition.  ...  Deep long-tailed learning, one of the most challenging problems in visual recognition, aims to train well-performing deep models from a large number of images that follow a long-tailed class distribution  ...  APPLICATIONS This section discusses the main visual applications of deep longtailed learning, including image classification, image detection and segmentation, and visual relation learning.  ... 
arXiv:2110.04596v1 fatcat:lpvt2x6cv5crxm2qxdctjrlkqq

Deep Transfer Learning for Modality Classification of Medical Images

Yuhai Yu, Hongfei Lin, Jiana Meng, Xiaocong Wei, Hai Guo, Zhehuan Zhao
2017 Information  
which imply that CNNs, based on our proposed transfer learning methods and data augmentation skills, can identify more efficiently modalities of medical images.  ...  The feature learning approach may detect efficiently visual characteristics of different modalities, but it is limited to the number of training datasets.  ...  Valavanis [12] adopts various visual features, such as Bag-of-Visual-Words [31] and Quad-Tree [32] BoC (Bag-of-Colors). Li, P. et al.  ... 
doi:10.3390/info8030091 fatcat:oarlhyedhjajxjsxr7ssru65jy

NADS-RA: Network Anomaly Detection Scheme Based on feature Representation and data Augmentation

Xu Liu, Xiaoqiang Di, Qiang Ding, Weiyou Liu, Hui Qi, Jinqing Li, Huamin Yang
2020 IEEE Access  
An image-based augmentation strategy is thus designed to produce augmented images according to the distribution characteristics of rare network anomaly images with the help of Least Squares Generative  ...  Data augmentation can tackle the imbalanced training set problem through creating artificial rare anomaly samples.  ...  Convolution neural network (CNN), as a type of deep learning algorithms, has achieved great classification performance in learning the spatial knowledge of images.  ... 
doi:10.1109/access.2020.3040510 fatcat:muqfbnj6kragdg5ui36afajxuy

Towards Representation Learning for Biomedical Concept Detection in Medical Images: UA.PT Bioinformatics in ImageCLEF 2017

Eduardo Pinho, João Figueira Silva, Jorge Miguel Silva, Carlos Costa
2017 Conference and Labs of the Evaluation Forum  
Test results showed a mean F1 score of 0.0488 and 0.0414 for the best run using bags of words and the autoencoder, respectively.  ...  The first approach consists of k-means clustering to create bags of words from SIFT descriptors. The second approach is based on a custom deep denoising convolutional autoencoder.  ...  Due to the inherent nature of medical imaging datasets, which are scarce and both frequently class-imbalanced and non-annotated, the rapid developments in deep learning and representation learning pose  ... 
dblp:conf/clef/PinhoSS017 fatcat:rcyeo3dzujco3ha7mcl67eifqe

Deep learning approach to description and classification of fungi microscopic images [article]

Bartosz Zieliński, Agnieszka Sroka-Oleksiak, Dawid Rymarczyk, Adam Piekarczyk, Monika Brzychczy-Włoch
2020 arXiv   pre-print
In this paper, we apply machine learning approach based on deep learning and bag-of-words to classify microscopic images of various fungi species.  ...  Diagnosis of fungal infections can rely on microscopic examination, however, in many cases, it does not allow unambiguous identification of the species due to their visual similarity.  ...  We apply data augmentation (rotations, mirror reflection, and random noise) for better regularization. The overall comparison of tested methods is presented in Table 1 .  ... 
arXiv:1906.09449v3 fatcat:t5zpqjzlrzc5rh3kjgo75oa55m

Detection and Classification of Pollen Grain Microscope Images

Sebastiano Battiato, Alessandro Ortis, Francesca Trenta, Lorenzo Ascari, Mara Politi, Consolata Siniscalco
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
Besides, we present the results obtained from the classification of these objects by taking advantage of several Machine Learning techniques, discussing which approaches have produced the most satisfactory  ...  Pollen identification and classification is a proper example to be treated in the Palynology field, which has been an expensive qualitative process, involving observation and discrimination of features  ...  Especially, they achieved the highest performance values when using features extracted from texture, color and shape in combination with a Bag of Visual Word (BOW), reporting a Correct Classification Rate  ... 
doi:10.1109/cvprw50498.2020.00498 dblp:conf/cvpr/BattiatoOTAPS20 fatcat:gxojahsv3bgmhanub6u3722usm

Machine Learning Algorithms for Depression: Diagnosis, Insights, and Research Directions

Shumaila Aleem, Noor ul Huda, Rashid Amin, Samina Khalid, Sultan S. Alshamrani, Abdullah Alshehri
2022 Electronics  
The ML-based depression detection algorithms are categorized into three classes, classification, deep learning, and ensemble.  ...  Machine learning (ML) has been accredited as an efficient approach for analyzing the massive amount of data in the healthcare domain.  ...  presents the comparison of DL models for depression. Figure 3 . 3 Figure 3. Comparison of deep learning models for depression diagnosis. Figure 3 . 3 Figure 3.  ... 
doi:10.3390/electronics11071111 fatcat:bx5z4vbqgrd67htkaz6rmt65ou

A Data Augmentation based Framework to Handle Class Imbalance Problem for Alzheimer's Stage Detection

Sitara Afzal, Muazzam Maqsood, Faria Nazir, Umair Khan, Farhan Aadil, Khalid Mahmood Awan, Irfan Mehmood, Oh-Young Song
2019 IEEE Access  
In this research, we employed a transfer learning-based technique using data augmentation for 3D Magnetic Resonance Imaging (MRI) views from OASIS dataset.  ...  However, the most common problem with deep learning architecture is that large training data is required.  ...  Altaf et al. in [4] proposed a state-of-the-art technique for the AD diagnosis utilizing the bag of words model attaining 79.8% accuracy for multi-class classification and 98.4% for binary class classification  ... 
doi:10.1109/access.2019.2932786 fatcat:jh2yfnjpbrgchirr6ecq35yaai

Dynamic Curriculum Learning for Imbalanced Data Classification

Yiru Wang, Weihao Gan, Jie Yang, Wei Wu, Junjie Yan
2019 2019 IEEE/CVF International Conference on Computer Vision (ICCV)  
; (2) loss scheduler which controls the learning importance between classification and metric learning loss.  ...  With these two schedulers, we achieve state-of-the-art performance on the widely used face attribute dataset CelebA and pedestrian attribute dataset RAP.  ...  CIFAR-100 [27] is a natural image classification dataset with 32 × 32 pixels. It contains 50,000 images for training and 10,000 images for testing. It is a balanced dataset with 100 classes.  ... 
doi:10.1109/iccv.2019.00512 dblp:conf/iccv/WangGYWY19 fatcat:kzthfmteorerdkbsg4h2ogtl24
« Previous Showing results 1 — 15 out of 666 results