Vitasd: Robust Vision Transformer Baselines for Autism Spectrum Disorder Facial Diagnosis

Cao, Xu; Ye, Wenqian; Sizikova, Elena; Bai, Xue; Coffee, Megan; Zeng, Hongwu; Cao, Jianguo

doi:10.1109/icassp49357.2023.10094684

Cited by 11 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By combining image classification with short behavioral observations and interviews, researchers may develop faster and more cost-effective alternatives to screening and diagnosis. The results obtained in our study align with those of other recent research papers on the topic, suggesting that autistic children may have subte facial characteristics that can be identified through machine learning (Ahmad et al, 2024;Cao et al, 2023;Gautam et al, 2023;Uddin et al, 2024). We extended past research by comparing two methods to examine the information that the models used to identify individuals with autism using facial images.…”

Section: Resultssupporting

confidence: 86%

“…Recently, some studies have addressed this issue by using machine learning and image classification to identify autistic children based on facial images (Ahmad et al, 2024;Cao et al, 2023;Gautam et al, 2023;Uddin et al, 2024). In the most accurate example reported in the research literature, Cao et al (2023) have produced models with an accuracy of 95% in differentiating autistic children from those who are not. Although the recent models have produced excellent accuracy, researchers have failed to pay attention to how and why these models produce their results.…”

Section: Recognize the Faces Of Autistic Childrenmentioning

confidence: 99%

See 1 more Smart Citation

Towards the Development of Explainable Machine Learning Models to Recognize the Faces of Autistic Children

Omrani,

Lanovaz,

Moroni

2024

Preprint

View full text Add to dashboard Cite

Machine learning with image classification has shown promise in supporting the detection of autism in children. To extend this line of work, our study compared the use of two algorithms to explain why an image is categorized as autistic or not. First, we trained and tested models on the Autistic Children Facial Image Data Set to identify the three that produced the highest accuracy. Following the identification of the three best models, we used two methods to examine explainability: Local Interpretable Model-agnostic Explanations (LIME) and Randomized Input Sampling for Explanation of Black-box Models (RISE). Overall, the best model produced an accuracy of 92% and LIME resulted in more explainable models than RISE. Albeit promising, researchers must conduct more studies to examine the generalizability of the results prior to the adoption of this model in practice.

show abstract

Section: Resultssupporting

confidence: 86%

Section: Recognize the Faces Of Autistic Childrenmentioning

confidence: 99%

Towards the Development of Explainable Machine Learning Models to Recognize the Faces of Autistic Children

Omrani,

Lanovaz,

Moroni

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Moreover, transformers suffer from high computational demand, complexity, and high training time. Cao et al (2023) [20] suggested using a Vision Transformer for analyzing pediatric ASD. The study uses a large facial dataset for performing model structure transferability and introduces a Gaussian Process layer for enhancing the robustness of the learning.…”

Section: Introductionmentioning

confidence: 99%

Autism Screening in Toddlers and Adults Using Deep Learning and Fair AI Techniques

Priyadarshini

2023

Future Internet

View full text Add to dashboard Cite

Autism spectrum disorder (ASD) has been associated with conditions like depression, anxiety, epilepsy, etc., due to its impact on an individual’s educational, social, and employment. Since diagnosis is challenging and there is no cure, the goal is to maximize an individual’s ability by reducing the symptoms, and early diagnosis plays a role in improving behavior and language development. In this paper, an autism screening analysis for toddlers and adults has been performed using fair AI (feature engineering, SMOTE, optimizations, etc.) and deep learning methods. The analysis considers traditional deep learning methods like Multilayer Perceptron (MLP), Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM), and also proposes two hybrid deep learning models, i.e., CNN–LSTM with Particle Swarm Optimization (PSO), and a CNN model combined with Gated Recurrent Units (GRU–CNN). The models have been validated using multiple performance metrics, and the analysis confirms that the proposed models perform better than the traditional models.

show abstract

Enhancing Autism Spectrum Classification using Super Resolution GAN and ViT based Embedding

Farooq,

Bin Amir,

Ejaz

et al. 2023

2023 20th International Bhurban Conference on Applied Sciences and Technology (IBCAST)

View full text Add to dashboard Cite

Vitasd: Robust Vision Transformer Baselines for Autism Spectrum Disorder Facial Diagnosis

Cited by 11 publications

References 15 publications

Towards the Development of Explainable Machine Learning Models to Recognize the Faces of Autistic Children

Towards the Development of Explainable Machine Learning Models to Recognize the Faces of Autistic Children

Autism Screening in Toddlers and Adults Using Deep Learning and Fair AI Techniques

Enhancing Autism Spectrum Classification using Super Resolution GAN and ViT based Embedding

Contact Info

Product

Resources

About