Opportunities and Challenges in Data-Centric AI
Artificial intelligence (AI) systems are trained to solve complex problems and learn to
perform specific tasks by using large volumes of data, such as prediction, classification …
perform specific tasks by using large volumes of data, such as prediction, classification …
Data-centric annotation analysis for plant disease detection: Strategy, consistency, and performance
Object detection models have become the current tool of choice for plant disease detection
in precision agriculture. Most existing research improved the performance by ameliorating …
in precision agriculture. Most existing research improved the performance by ameliorating …
Why does little robustness help? a further step towards understanding adversarial transferability
Adversarial examples for deep neural networks (DNNs) are transferable: examples that
successfully fool one white-box surrogate model can also deceive other black-box models …
successfully fool one white-box surrogate model can also deceive other black-box models …
A Data-Centric AI Paradigm for Socio-Industrial and Global Challenges
A Majeed, SO Hwang - Electronics, 2024 - mdpi.com
Due to huge investments by both the public and private sectors, artificial intelligence (AI) has
made tremendous progress in solving multiple real-world problems such as disease …
made tremendous progress in solving multiple real-world problems such as disease …
Skeleton-based human action recognition via convolutional neural networks (CNN)
A Ali, E Pinyoanuntapong, P Wang… - arXiv preprint arXiv …, 2023 - arxiv.org
Recently, there has been a remarkable increase in the interest towards skeleton-based
action recognition within the research community, owing to its various advantageous …
action recognition within the research community, owing to its various advantageous …
Robustness and Transferability of Adversarial Attacks on Different Image Classification Neural Networks
Recent works demonstrated that imperceptible perturbations to input data, known as
adversarial examples, can mislead neural networks' output. Moreover, the same adversarial …
adversarial examples, can mislead neural networks' output. Moreover, the same adversarial …
Harnessing the Power of Noise: A Survey of Techniques and Applications
Noise, traditionally considered a nuisance in computational systems, is reconsidered for its
unexpected and counter-intuitive benefits across a wide spectrum of domains, including …
unexpected and counter-intuitive benefits across a wide spectrum of domains, including …
[PDF][PDF] Towards Improved Performance on Plant Disease Recognition with Symptoms Specific Annotation
Object detection models have become the current tool of choice for plant disease detection
in precision agriculture. Most existing research improves the performance by ameliorating …
in precision agriculture. Most existing research improves the performance by ameliorating …
YOLOv5-GT: A Balanced Improvement in Object Detection Speed and Accuracy for Autonomous Vehicles in Indonesian Mixed Traffic
SS Saesaria, BR Trilaksono… - 2024 14th International …, 2024 - ieeexplore.ieee.org
Object detection speed and accuracy are critical aspects of the perception system in
autonomous vehicles. Speed improvement helps the object detector model achieve …
autonomous vehicles. Speed improvement helps the object detector model achieve …
Self-Improving-Leaderboard (SIL): A Call for Real-World Centric Natural Language Processing Leaderboards
Leaderboard systems allow researchers to objectively evaluate Natural Language
Processing (NLP) models and are typically used to identify models that exhibit superior …
Processing (NLP) models and are typically used to identify models that exhibit superior …