“Generalization of convolutional network to domain adaptation network for classification of disaster images on twitter”

Khattar, Anuradha; Quadri, S. M. K.

doi:10.1007/s11042-022-12869-1

Cited by 18 publications

(6 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dimensions of the last three dense layers in block 6 are each 4096, 4096, and 1000. VGG classifies the input image into 1000 different categories (Khattar & Quadri, 2022).…”

Section: Literature Reviewmentioning

confidence: 99%

Pneumonia Classification Based on Lung CT Scans Using Vgg-19

Putra,

Situmorang,

Wahyudi

et al. 2023

SinkrOn

View full text Add to dashboard Cite

This research harnesses technology for critical health applications, specifically, pneumonia detection through medical imaging. X-ray photography allows radiologists to visualize the patient's health state, including the detection of lung infections signifying pneumonia. The study's centerpiece is the application of the VGG-19 model in classifying lung CT scan images, helping discern normal from pneumonia-indicative conditions. A comprehensive preprocessing procedure is employed, entailing pixel rescaling and data augmentation techniques. To address data imbalance, a critical issue in machine learning, we incorporate the Synthetic Minority Over-sampling Technique (SMOTE). The developed VGG-19 model demonstrates impressive performance, achieving a 94.6% accuracy rate in classifying lung CT scans. This finding underscores the potential of the VGG-19 model as a reliable tool for pneumonia detection based on lung CT scans. Such a tool could revolutionize the field, providing an efficient and accurate method for early pneumonia diagnosis, thereby allowing for timely treatment.

show abstract

“…The dimensions of the last three dense layers in block 6 are each 4096, 4096, and 1000. VGG classifies the input image into 1000 different categories (Khattar & Quadri, 2022).…”

Section: Literature Reviewmentioning

confidence: 99%

Pneumonia Classification Based on Lung CT Scans Using Vgg-19

Putra,

Situmorang,

Wahyudi

et al. 2023

SinkrOn

View full text Add to dashboard Cite

show abstract

“…Liang et al [18] fine-tuned pre-trained convolutional and language models using multimodal inputs of text-image pairs and obtained effective results against multimodal classification benchmarks. Khattar and Quadri [19] utilized unsupervised domain adaptation to classify unlabeled data of a new disaster using the existing labeled images of relevant disasters.…”

Section: Disaster Classificationmentioning

confidence: 99%

Efficient Classification of Imbalanced Natural Disasters Data Using Generative Adversarial Networks for Data Augmentation

Eltehewy,

Abouelfarag,

Saleh

2023

IJGI

View full text Add to dashboard Cite

Rapid damage identification and classification in disastrous situations and natural disasters are crucial for efficiently directing aid and resources. With the development of deep learning techniques and the availability of imagery content on social media platforms, extensive research has focused on damage assessment. Through the use of geospatial data related to such incidents, the visual characteristics of these images can quickly determine the safety situation in the region. However, training accurate disaster classification models has proven to be challenging due to the lack of labeled imagery data in this domain. This paper proposes a disaster classification framework, which combines a set of synthesized diverse disaster images generated using generative adversarial networks (GANs) and domain-specific fine-tuning of a deep convolutional neural network (CNN)-based model. The proposed model utilizes bootstrap aggregating (bagging) to further stabilize the target predictions. Since past work in this domain mainly suffers from limited data resources, a sample dataset that highlights the issue of imbalanced classification of multiple natural disasters was constructed and augmented. Qualitative and quantitative experiments show the validity of the data augmentation method employed in producing a balanced dataset. Further experiments with various evaluation metrics verified the proposed framework’s accuracy and generalization ability across different classes for the task of disaster classification in comparison to other state-of-the-art techniques. Furthermore, the framework outperforms the other models by an average validation accuracy of 11%. These results provide a deep learning solution for real-time disaster monitoring systems to mitigate the loss of lives and properties.

show abstract

“…Since labeling is a tedious and expensive task, self-labeling [47], [48], synthetic labeling [49], and semi-supervised learning [50] methods have also been proposed recently. At the onset of a disaster, the unavailability of labeled data has also encouraged researchers to propose methods based on transfer learning and domain adaptation [16], [51]. Li et al were among the first few researchers to explore this area.…”

Section: B Unimodal: Based On Image-only Modalitymentioning

confidence: 99%

CAMM: Cross-Attention Multimodal Classification of Disaster-Related Tweets

Khattar

Quadri

2022

IEEE Access

Self Cite

View full text Add to dashboard Cite

During the past decade, social media platforms have been extensively used during a disaster for information dissemination by the affected community and humanitarian agencies. Although many studies have been done recently to classify the informative and non-informative messages from social media posts, most are unimodal, i.e., have independently used textual or visual data to build the deep learning models. In the present study, we integrate the complementary information provided by the text and image messages about the same event posted by the affected community on the social media platform Twitter and build a multimodal deep learning model based on the concept of attention mechanism. The attention mechanism is a recent breakthrough that has revolutionized the field of deep learning. Just as humans pay more attention to a specific part of the text or image, ignoring the rest, neural networks can also be trained to concentrate on more relevant features through the attention mechanism. We propose a novel Cross-Attention Multi-Modal (CAMM) deep neural network for classifying multimodal disaster data, which uses the attention mask of the textual modality to highlight the features of the visual modality. We compare CAMM with unimodal models and the most popular bilinear multimodal models, MUTAN and BLOCK, generally used for visual question answering. CAMM achieves an average F1-score of 84.08%, better than the MUTAN and BLOCK methods by 6.31% and 5.91%, respectively. The proposed crossattention-based multimodal deep learning method outperforms the current state-of-the-art fusion methods on the benchmark multimodal disaster dataset by highlighting the more relevant cross-domain features of text and image tweets. This study affirms that social media platforms become a rich source of multimodal data during a disaster. This data can be utilized to build automated tools for quick filtration of informative messages to assess the post-disaster needs of the affected community and provide timely help.

show abstract

“Generalization of convolutional network to domain adaptation network for classification of disaster images on twitter”

Cited by 18 publications

References 38 publications

Pneumonia Classification Based on Lung CT Scans Using Vgg-19

Pneumonia Classification Based on Lung CT Scans Using Vgg-19

Efficient Classification of Imbalanced Natural Disasters Data Using Generative Adversarial Networks for Data Augmentation

CAMM: Cross-Attention Multimodal Classification of Disaster-Related Tweets

Contact Info

Product

Resources

About