Deep Learning in Computer Vision: Methods, Interpretation, Causation, and Fairness

Malik, Nikhil; Singh, Param Vir

doi:10.1287/educ.2019.0201

Cited by 11 publications

(5 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Techniques like domain adaptation [26] and generalization [27] have emerged to bridge distribution gaps. Still, challenges persist, particularly with model interpretability [25]. Thus, while current methods prioritize function approximation, a more analytical approach could optimize generalizability and interpretability.…”

Section: Of 21mentioning

confidence: 99%

“…In the real deep learning-based computer vision classification tasks, the typical objective revolves around effectively handling images denoted as X. The overarching aim is to train a neural network capable of accurately predicting the corresponding label Y [25]. To achieve this, a statistical model is employed, tailored with a well-suited objective function, which in turn helps estimate the conditional probability distribution P(Y|X).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Computer Vision with Causal Inference/Learning: A Deep Learning Approach Notes

Hambarde

2023

Preprint

View full text Add to dashboard Cite

Deep learning heavily relies on statistical correlations to drive artificial intelligence (AI) innovations, particularly in computer vision applications like autonomous driving and robotics. However, despite providing a solid foundation for deep learning, these statistical correlations can be vulnerable to unforeseen and uncontrolled factors. The lack of prior knowledge guidance can result in spurious correlations, introducing confounding factors and affecting the model's robustness. To address this challenge, recent research efforts have focused on integrating causal theory into deep learning methodologies. By modelling the inherent and unbiased causal structure, causal theory can potentially mitigate the impact of spurious correlations effectively. Hence, this paper explores the basics of causal methodologies in image classification.

show abstract

Section: Of 21mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Computer Vision with Causal Inference/Learning: A Deep Learning Approach Notes

Hambarde

2023

Preprint

View full text Add to dashboard Cite

show abstract

Section: Image-based Affective Computingmentioning

confidence: 99%

“…Another study by Wen et al (2016) focused on intra-class compactness for facial recognition. Deep learning finds its application in computer vision, including image and video data (Malik and Singh, 2019). One of the latest studies by Guan et al (2019) has proposed a deep learning-based recommendation tool named Deep-MINE, which integrates multiple sources of content such as product images, product descriptions and review comments for recommendation purposes.…”

Section: Related Workmentioning

confidence: 99%

Deep learning based affective computing

Kumar

2021

JEIM

View full text Add to dashboard Cite

PurposeDecision-making in human beings is affected by emotions and sentiments. The affective computing takes this into account, intending to tailor decision support to the emotional states of people. However, the representation and classification of emotions is a very challenging task. The study used customized methods of deep learning models to aid in the accurate classification of emotions and sentiments.Design/methodology/approachThe present study presents affective computing model using both text and image data. The text-based affective computing was conducted on four standard datasets using three deep learning customized models, namely LSTM, GRU and CNN. The study used four variants of deep learning including the LSTM model, LSTM model with GloVe embeddings, Bi-directional LSTM model and LSTM model with attention layer.FindingsThe result suggests that the proposed method outperforms the earlier methods. For image-based affective computing, the data was extracted from Instagram, and Facial emotion recognition was carried out using three deep learning models, namely CNN, transfer learning with VGG-19 model and transfer learning with ResNet-18 model. The results suggest that the proposed methods for both text and image can be used for affective computing and aid in decision-making.Originality/valueThe study used deep learning for affective computing. Earlier studies have used machine learning algorithms for affective computing. However, the present study uses deep learning for affective computing.

show abstract

“…Several studies examined distinct machine/deep learning methods for medical imaging diagnosis [5][6][7]. Deep learning has gained remarkable success in computer vision for medical imaging [8]. Convolutional neural networks (CNNs) are the most popular network in computer vision.…”

Section: Introductionmentioning

confidence: 99%

Hyperparameters optimization for ResNet and Xception in the purpose of diagnosing COVID-19

Farag

Said

Rizk

et al. 2021

IFS

View full text Add to dashboard Cite

COVID-19 has been considered as a global pandemic. Recently, researchers are using deep learning networks for medical diseases’ diagnosis. Some of these researches focuses on optimizing deep learning neural networks for enhancing the network accuracy. Optimizing the Convolutional Neural Network includes testing various networks which are obtained through manually configuring their hyperparameters, then the configuration with the highest accuracy is implemented. Each time a different database is used, a different combination of the hyperparameters is required. This paper introduces two COVID-19 diagnosing systems using both Residual Network and Xception Network optimized by random search in the purpose of finding optimal models that give better diagnosis rates for COVID-19. The proposed systems showed that hyperparameters tuning for the ResNet and the Xception Net using random search optimization give more accurate results than other techniques with accuracies 99.27536% and 100 % respectively. We can conclude that hyperparameters tuning using random search optimization for either the tuned Residual Network or the tuned Xception Network gives better accuracies than other techniques diagnosing COVID-19.

show abstract

Deep Learning in Computer Vision: Methods, Interpretation, Causation, and Fairness

Cited by 11 publications

References 36 publications

Computer Vision with Causal Inference/Learning: A Deep Learning Approach Notes

Computer Vision with Causal Inference/Learning: A Deep Learning Approach Notes

Deep learning based affective computing

Hyperparameters optimization for ResNet and Xception in the purpose of diagnosing COVID-19

Contact Info

Product

Resources

About