1 code implementation • 13 Nov 2023 • Jiazhi Li, Mahyar Khayatkhoei, Jiageng Zhu, Hanchen Xie, Mohamed E. Hussein, Wael AbdAlmageed
To that end, in this work, we mathematically and empirically reveal the limitation of existing attribute bias removal methods in presence of strong bias and propose a new method that can mitigate this limitation.
1 code implementation • 8 Oct 2023 • Jiazhi Li, Mahyar Khayatkhoei, Jiageng Zhu, Hanchen Xie, Mohamed E. Hussein, Wael AbdAlmageed
Ensuring a neural network is not relying on protected attributes (e. g., race, sex, age) for predictions is crucial in advancing fair and trustworthy AI.
1 code implementation • 10 Aug 2023 • Jiageng Zhu, Hanchen Xie, Jianhua Wu, Jiazhi Li, Mahyar Khayatkhoei, Mohamed E. Hussein, Wael AbdAlmageed
Most causal representation learning (CRL) methods are fully supervised, which is impractical due to costly labeling.
no code implementations • 8 Jun 2023 • Mohamed E. Hussein, Sudharshan Subramaniam Janakiraman, Wael AbdAlmageed
TRIGS delivers the best performance on the new dataset, surpassing the baseline methods by a large margin.
1 code implementation • 12 May 2023 • Hanchen Xie, Jiageng Zhu, Mahyar Khayatkhoei, Jiazhi Li, Mohamed E. Hussein, Wael AbdAlmageed
In this paper, we investigate two challenging conditions for environment misalignment: Cross-Domain and Cross-Context by proposing four datasets that are designed for these challenges: SimB-Border, SimB-Split, BlenB-Border, and BlenB-Split.
no code implementations • 8 Nov 2021 • Hengameh Mirzaalian, Mohamed E. Hussein, Leonidas Spinoulas, Jonathan May, Wael Abd-Almageed
Due to the limited amount of annotated data in our study, we apply a light-weight LSTM network as our natural language generation model.
no code implementations • 30 Sep 2021 • Mohamed E. Hussein, Wael AbdAlmageed
The function can also be extended to the case of multi-class classification, and used as an alternative to the standard softmax function.
2 code implementations • IEEE Access 2021 • HEBA HASSAN1, Ahmed El-Mahdy, Mohamed E. Hussein
Therefore, we use our new dataset to evaluate the problem of Arabic scene text recognition from three perspectives: (1) using deep learning techniques and studying their suitability for Arabic scene text recognition, where we identify essential components required for the model to obtain good performance; (2) identifying Arabic text challenges that differ from Latin text and require special attention; (3) investigating a bilingual model that concurrently deals with Arabic and English words, since Arabic text is usually found along with other languages.
1 code implementation • International Conference of Computer Vision Theory and Application 2021 • Heba Hassan, Marwan Torki, Mohamed E. Hussein
Alternatively, it can also be posed as a character prediction problem.
no code implementations • 1 Jan 2021 • Ehsan Kazemi, Mohamed E. Hussein, Wael AbdAlmgaeed
We propose an ensemble-based defense against adversarial examples using distance map layers (DMLs).
no code implementations • 30 Nov 2020 • Hanchen Xie, Mohamed E. Hussein, Aram Galstyan, Wael Abd-Almageed
We also show that MUSCLE has the potential to boost the classification performance when used in the fine-tuning phase for a model pre-trained only on unlabeled data.
1 code implementation • 23 May 2017 • Ahmed Ibrahim, A. Lynn Abbott, Mohamed E. Hussein
This scheme is substantially different from "deep supervision" in which the loss layer is re-introduced to earlier layers.
no code implementations • 20 Oct 2016 • Ahmed Ibrahim, A. Lynn Abbott, Mohamed E. Hussein
Although much research has been devoted to text detection and recognition in scanned documents, relatively little attention has been given to text detection in other types of images, such as photographs that are posted on social-media sites.
no code implementations • 4 Feb 2015 • Moustafa Meshry, Mohamed E. Hussein, Marwan Torki
It identifies the sub-interval with the maximum classifier score in linear time.
no code implementations • 17 Nov 2014 • Mohamed E. Hussein, Marwan Torki, Ahmed Elsallamy, Mahmoud Fayyaz
The end goal is to collect a very large dataset of segmented letter images, which can be used to build and evaluate Arabic handwriting recognition systems that are based on segmented letter recognition.
no code implementations • 13 Nov 2014 • Marwan Torki, Mohamed E. Hussein, Ahmed Elsallamy, Mahmoud Fayyaz, Shehab Yaser
This paper presents a comparative study for window-based descriptors on the application of Arabic handwritten alphabet recognition.