Progressive Transmission and Inference of Deep Learning Models

Lee, Youngsoo; Yun, Sangdoo; Kim, Yeonghun; Choi, Sunghee

doi:10.1109/icmla52953.2021.00049

Cited by 6 publications

(9 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A progressive transfer framework for deep learning models is introduced in [76] by using the principle of transferring large image files over the web. The framework enables a deep learning model to be divided and progressively transferred in stages.…”

Section: Optimizing the Model Prior To Deploymentmentioning

confidence: 99%

Front-end deep learning web apps development and deployment: a review

Goh

Abas

2022

Appl Intell

View full text Add to dashboard Cite

Machine learning and deep learning models are commonly developed using programming languages such as Python, C++, or R and deployed as web apps delivered from a back-end server or as mobile apps installed from an app store. However, recently front-end technologies and JavaScript libraries, such as TensorFlow.js, have been introduced to make machine learning more accessible to researchers and end-users. Using JavaScript, TensorFlow.js can define, train, and run new or existing, pre-trained machine learning models entirely in the browser from the client-side, which improves the user experience through interaction while preserving privacy. Deep learning models deployed on front-end browsers must be small, have fast inference, and ideally be interactive in real-time. Therefore, the emphasis on development and deployment is different. This paper aims to review the development and deployment of these deep-learning web apps to raise awareness of the recent advancements and encourage more researchers to take advantage of this technology for their own work. First, the rationale behind the deployment stack (front-end, JavaScript, and TensorFlow.js) is discussed. Then, the development approach for obtaining deep learning models that are optimized and suitable for front-end deployment is then described. The article also provides current web applications divided into seven categories to show deep learning potential on the front end. These include web apps for deep learning playground, pose detection and gesture tracking, music and art creation, expression detection and facial recognition, video segmentation, image and signal analysis, healthcare diagnosis, recognition, and identification.

show abstract

Section: Optimizing the Model Prior To Deploymentmentioning

confidence: 99%

Front-end deep learning web apps development and deployment: a review

Goh

Abas

2022

Appl Intell

View full text Add to dashboard Cite

show abstract

“…It is well established that deep learningbased supervised medical image classification requires accurately annotated labels to effectively train classification models. Supervised training with inaccurately annotated or noisy labels can impair a model's generalizability, resulting in subpar test performance [13], [27], [11], [10].…”

Section: Introductionmentioning

confidence: 99%

Investigating the impact of class-dependent label noise in medical image classification

Khanal

Hasan

Khanal

et al. 2023

Medical Imaging 2023: Image Processing

View full text Add to dashboard Cite

Label noise is inevitable in medical image databases developed for deep learning due to the inter-observer variability caused by the different levels of expertise of the experts annotating the images, and, in some cases, the automated methods that generate labels from medical reports. It is known that incorrect annotations or label noise can degrade the actual performance of supervised deep learning models and can bias the model's evaluation. Existing literature show that noise in one class has minimal impact on the model's performance for another class in natural image classification problems where different target classes have a relatively distinct shape and share minimal visual cues for knowledge transfer among the classes. However, it is not clear how classdependent label noise affects the model's performance when operating on medical images, for which different output classes can be difficult to distinguish even for experts, and there is a high possibility of knowledge transfer across classes during the training period. We hypothesize that for medical image classification tasks where the different classes share a very similar shape with differences only in texture, the noisy label for one class might affect the performance across other classes, unlike the case when the target classes have different shapes and are visually distinct. In this paper, we study this hypothesis using two publicly available datasets: a 2D organ classification dataset with target organ classes being visually distinct, and a histopathology image classification dataset where the target classes look very similar visually. Our results show that the label noise in one class has a much higher impact on the model's performance on other classes for the histopathology dataset compared to the organ dataset.

show abstract

“…However, yet to date, the community still has a limited understanding of the fundamental cause and mitigation of the overconfidence issue. Furthermore, existing robust algorithms only utilize in-distribution data for training and typically considered out-of-distribution (OOD) examples to be harmful to the training of deep neural networks [32][33][34][35].…”

Section: Motivationsmentioning

confidence: 99%

“…Label noise can be separated into two categories: 1) closed-set noise, where instances with noisy labels have true class labels within the noisy label set [27,59,63,67,69,160]. 2) open-set noise, where instances with noisy labels have some true class labels outside the noisy label set [32][33][34][35]. In the existing literature, open-set noises are always considered to be harmful to the training of DNNs like closed-set noises [32][33][34][35].…”

Section: Motivationmentioning

confidence: 99%

“…2) open-set noise, where instances with noisy labels have some true class labels outside the noisy label set [32][33][34][35]. In the existing literature, open-set noises are always considered to be harmful to the training of DNNs like closed-set noises [32][33][34][35]. For example, ILON [33] reduces the effect of open-set noises by using noisy label detector and contrastive loss to pull away noisy samples from clean samples.…”

Section: Motivationmentioning

confidence: 99%

See 1 more Smart Citation

Natural robustness of machine learning in the open world

Wei¹

View full text Add to dashboard Cite

visor, Prof. Bo An. Without the great opportunity he provided, I could not have undertaken this Ph.D. journey, which has been a turning point in my life. During these years, he always maintains a gentle, patient, and kind style. He has not only provided a singularly suitable research environment with the greatest freedom, but also taught me the necessary knowledge in my research life, such as how to be professional and how to properly communicate with others. Words cannot express my gratitude to him. The experience in his group would definitely shape my future in many dimensions. I am so fortunate to become a Ph.D. student under his supervision and I wish to be such a nice professor like him in the future. I also had the pleasure of working with a group of talented people: Qingyu Guo,

show abstract

Progressive Transmission and Inference of Deep Learning Models

Cited by 6 publications

References 17 publications

Front-end deep learning web apps development and deployment: a review

Front-end deep learning web apps development and deployment: a review

Investigating the impact of class-dependent label noise in medical image classification

Natural robustness of machine learning in the open world

Contact Info

Product

Resources

About