no code implementations • 20 Oct 2023 • Aminul Huq, Dimitris Zermas, George Bebis
Using deep learning techniques, we have developed a methodology which can detect different levels of abnormality (i. e., low, medium, high or no abnormality) in maize plants independently of their growth stage.
no code implementations • 10 Mar 2023 • Aminul Huq, Weiyi Zhang, Xiaolin Hu
We merge the capabilities of both supervised and unsupervised approaches in our method to generate new adversarial samples which aid in improving model robustness.
no code implementations • 10 Mar 2023 • Aminul Huq, Md Tanzim Reza, Shahriar Hossain, Shakib Mahmud Dipto
Class imbalance is a pervasive issue in the field of disease classification from medical images.
no code implementations • 10 Mar 2023 • Aminul Huq, Mst Tasnim Pervin
To train a model in multi-task learning settings we need to sum the loss values from different tasks.
no code implementations • 25 May 2021 • Mst. Tasnim Pervin, Linmi Tao, Aminul Huq, Zuoxiang He, Li Huo
Furthermore, We have also introduced the concept of Inverse FGSM (InvFGSM), which works in the opposite manner of FGSM for the data augmentation.
no code implementations • 28 May 2020 • Aminul Huq, Mst. Tasnim Pervin
Deep learning models have been used widely for various purposes in recent years in object recognition, self-driving cars, face recognition, speech recognition, sentiment analysis, and many others.