Wael AbdAlmageed
YOU?
Author Swipe
View article: A Critical Review of Predominant Bias in Neural Networks
A Critical Review of Predominant Bias in Neural Networks Open
Bias issues of neural networks garner significant attention along with its promising advancement. Among various bias issues, mitigating two predominant biases is crucial in advancing fair and trustworthy AI: (1) ensuring neural networks yi…
View article: Look, Learn and Leverage (L$^3$): Mitigating Visual-Domain Shift and Discovering Intrinsic Relations via Symbolic Alignment
Look, Learn and Leverage (L$^3$): Mitigating Visual-Domain Shift and Discovering Intrinsic Relations via Symbolic Alignment Open
Modern deep learning models have demonstrated outstanding performance on discovering the underlying mechanisms when both visual appearance and intrinsic relations (e.g., causal structure) data are sufficient, such as Disentangled Represent…
View article: An Investigation on The Position Encoding in Vision-Based Dynamics Prediction
An Investigation on The Position Encoding in Vision-Based Dynamics Prediction Open
Despite the success of vision-based dynamics prediction models, which predict object states by utilizing RGB images and simple object descriptions, they were challenged by environment misalignments. Although the literature has demonstrated…
View article: ManiFPT: Defining and Analyzing Fingerprints of Generative Models
ManiFPT: Defining and Analyzing Fingerprints of Generative Models Open
Recent works have shown that generative models leave traces of their underlying generative process on the generated samples, broadly referred to as fingerprints of a generative model, and have studied their utility in detecting synthetic i…
View article: Unsupervised Multimodal Deepfake Detection Using Intra- and Cross-Modal Inconsistencies
Unsupervised Multimodal Deepfake Detection Using Intra- and Cross-Modal Inconsistencies Open
Deepfake videos present an increasing threat to society with potentially negative impact on criminal justice, democracy, and personal safety and privacy. Meanwhile, detecting deepfakes, at scale, remains a very challenging task that often …
View article: SABAF: Removing Strong Attribute Bias from Neural Networks with Adversarial Filtering
SABAF: Removing Strong Attribute Bias from Neural Networks with Adversarial Filtering Open
Ensuring a neural network is not relying on protected attributes (e.g., race, sex, age) for prediction is crucial in advancing fair and trustworthy AI. While several promising methods for removing attribute bias in neural networks have bee…
View article: Information-Theoretic Bounds on The Removal of Attribute-Specific Bias From Neural Networks
Information-Theoretic Bounds on The Removal of Attribute-Specific Bias From Neural Networks Open
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. While several promising methods for removing attribute bias in neural networks have be…
View article: Shadow Datasets, New challenging datasets for Causal Representation Learning
Shadow Datasets, New challenging datasets for Causal Representation Learning Open
Discovering causal relations among semantic factors is an emergent topic in representation learning. Most causal representation learning (CRL) methods are fully supervised, which is impractical due to costly labeling. To resolve this restr…
View article: TrainFors: A Large Benchmark Training Dataset for Image Manipulation Detection and Localization
TrainFors: A Large Benchmark Training Dataset for Image Manipulation Detection and Localization Open
The evaluation datasets and metrics for image manipulation detection and localization (IMDL) research have been standardized. But the training dataset for such a task is still nonstandard. Previous researchers have used unconventional and …
View article: Emergent Asymmetry of Precision and Recall for Measuring Fidelity and Diversity of Generative Models in High Dimensions
Emergent Asymmetry of Precision and Recall for Measuring Fidelity and Diversity of Generative Models in High Dimensions Open
Precision and Recall are two prominent metrics of generative performance, which were proposed to separately measure the fidelity and diversity of generative models. Given their central role in comparing and improving generative models, und…
View article: TRIGS: Trojan Identification from Gradient-based Signatures
TRIGS: Trojan Identification from Gradient-based Signatures Open
Training machine learning models can be very expensive or even unaffordable. This may be, for example, due to data limitations, such as unavailability or being too large, or computational power limitations. Therefore, it is a common practi…
View article: SW-VAE: Weakly Supervised Learn Disentangled Representation Via Latent Factor Swapping
SW-VAE: Weakly Supervised Learn Disentangled Representation Via Latent Factor Swapping Open
Representation disentanglement is an important goal of representation learning that benefits various downstream tasks. To achieve this goal, many unsupervised learning representation disentanglement approaches have been developed. However,…
View article: Weakly Supervised Invariant Representation Learning Via Disentangling Known and Unknown Nuisance Factors
Weakly Supervised Invariant Representation Learning Via Disentangling Known and Unknown Nuisance Factors Open
Disentangled and invariant representations are two critical goals of representation learning and many approaches have been proposed to achieve either one of them. However, those two goals are actually complementary to each other so that we…
View article: CAT: Controllable Attribute Translation for Fair Facial Attribute Classification
CAT: Controllable Attribute Translation for Fair Facial Attribute Classification Open
As the social impact of visual recognition has been under scrutiny, several protected-attribute balanced datasets emerged to address dataset bias in imbalanced datasets. However, in facial attribute classification, dataset bias stems from …
View article: MONet: Multi-scale Overlap Network for Duplication Detection in Biomedical Images
MONet: Multi-scale Overlap Network for Duplication Detection in Biomedical Images Open
Manipulation of biomedical images to misrepresent experimental results has plagued the biomedical community for a while. Recent interest in the problem led to the curation of a dataset and associated tasks to promote the development of bio…
View article: Learning Robust Representations Of Generative Models Using Set-Based Artificial Fingerprints
Learning Robust Representations Of Generative Models Using Set-Based Artificial Fingerprints Open
With recent progress in deep generative models, the problem of identifying synthetic data and comparing their underlying generative processes has become an imperative task for various reasons, including fighting visual misinformation and s…
View article: Do-Operation Guided Causal Representation Learning with Reduced Supervision Strength
Do-Operation Guided Causal Representation Learning with Reduced Supervision Strength Open
Causal representation learning has been proposed to encode relationships between factors presented in the high dimensional data. However, existing methods suffer from merely using a large amount of labeled data and ignore the fact that sam…
View article: Attack-Agnostic Adversarial Detection
Attack-Agnostic Adversarial Detection Open
The growing number of adversarial attacks in recent years gives attackers an advantage over defenders, as defenders must train detectors after knowing the types of attacks, and many models need to be maintained to ensure good performance i…
View article: P2M-DeTrack: Processing-in-Pixel-in-Memory for Energy-efficient and Real-Time Multi-Object Detection and Tracking
P2M-DeTrack: Processing-in-Pixel-in-Memory for Energy-efficient and Real-Time Multi-Object Detection and Tracking Open
Today's high resolution, high frame rate cameras in autonomous vehicles generate a large volume of data that needs to be transferred and processed by a downstream processor or machine learning (ML) accelerator to enable intelligent computi…
View article: Explaining Face Presentation Attack Detection Using Natural Language
Explaining Face Presentation Attack Detection Using Natural Language Open
A large number of deep neural network based techniques have been developed to address the challenging problem of face presentation attack detection (PAD). Whereas such techniques' focus has been on improving PAD performance in terms of cla…
View article: Automatic Detection and Classification of Rock Microstructures through Machine Learning
Automatic Detection and Classification of Rock Microstructures through Machine Learning Open
Earth and Space Science Open Archive PosterOpen AccessYou are viewing the latest version by default [v1]Automatic Detection and Classification of Rock Microstructures through Machine LearningAuthorsStephenIotaJunyiLiuMingLyuBolongPanXiaoyu…
View article: Information-Theoretic Bias Assessment Of Learned Representations Of Pretrained Face Recognition
Information-Theoretic Bias Assessment Of Learned Representations Of Pretrained Face Recognition Open
As equality issues in the use of face recognition have garnered a lot of attention lately, greater efforts have been made to debiased deep learning models to improve fairness to minorities. However, there is still no clear definition nor s…
View article: Detection and Continual Learning of Novel Face Presentation Attacks
Detection and Continual Learning of Novel Face Presentation Attacks Open
Advances in deep learning, combined with availability of large datasets, have led to impressive improvements in face presentation attack detection research. However, state-of-the-art face antispoofing systems are still vulnerable to novel …
View article: BioFors: A Large Biomedical Image Forensics Dataset
BioFors: A Large Biomedical Image Forensics Dataset Open
Research in media forensics has gained traction to combat the spread of misinformation. However, most of this research has been directed towards content generated on social media. Biomedical image forensics is a related problem, where mani…
View article: Introducing the DOME Activation Functions
Introducing the DOME Activation Functions Open
In this paper, we introduce a novel non-linear activation function that spontaneously induces class-compactness and regularization in the embedding space of neural networks. The function is dubbed DOME for Difference Of Mirrored Exponentia…
View article: Partner-Assisted Learning for Few-Shot Image Classification
Partner-Assisted Learning for Few-Shot Image Classification Open
Few-shot Learning has been studied to mimic human visual capabilities and learn effective models without the need of exhaustive human annotation. Even though the idea of meta-learning for adaptation has dominated the few-shot learning meth…
View article: SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation
SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation Open
Unlike conventional zero-shot classification, zero-shot semantic segmentation predicts a class label at the pixel level instead of the image level. When solving zero-shot semantic segmentation problems, the need for pixel-level prediction …
View article: Adversarial Defense for Deep Speaker Recognition Using Hybrid Adversarial Training
Adversarial Defense for Deep Speaker Recognition Using Hybrid Adversarial Training Open
Deep neural network based speaker recognition systems can easily be deceived by an adversary using minuscule imperceptible perturbations to the input speech samples. These adversarial attacks pose serious security threats to the speaker re…
View article: Multispectral Biometrics System Framework: Application to Presentation Attack Detection
Multispectral Biometrics System Framework: Application to Presentation Attack Detection Open
In this work, we present a general framework for building a biometrics system capable of capturing multispectral data from a series of sensors synchronized with active illumination sources. The framework unifies the system design for diffe…