20 citations · 28 across the 20 of their papers we have counts for
20 papers
iStructTab: Structured Feature Sequencing for Multimodal Learning of Image and Tabular Data
Al Zadid Sultan Bin Habib, Md Younus Ahamed, Prashnna Gyawali +2
Multimodal learning of images and tabular data is often impaired by ineffective representations, resulting in redundancy, dispersion, and generalization problems. To tackle this ch…
Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation
Ahsan Habib Akash, Dipkamal Bhusal, Stacey Jones +3
Deep neural networks are widely deployed in high-stakes visual applications where interpretability is critical, yet existing explanations face a trade-off: post-hoc concept methods…
DynaTab: Dynamic Feature Ordering as Neural Rewiring for High-Dimensional Tabular Data
Al Zadid Sultan Bin Habib, Gianfranco Doretto, Donald A. Adjeroh
High-dimensional tabular data lacks a natural feature order, limiting the applicability of permutation-sensitive deep learning models. We propose DynaTab, a dynamic feature orderin…
FedVG: Gradient-Guided Aggregation for Enhanced Federated Learning
Alina Devkota, Jacob Thrasher, Donald Adjeroh +2
Federated Learning (FL) enables collaborative model training across multiple clients without sharing their private data. However, data heterogeneity across clients leads to client…
GUESS: Generative Uncertainty Ensemble for Self Supervision
Salman Mohamadi, Gianfranco Doretto, Donald A. Adjeroh
Self-supervised learning (SSL) frameworks consist of pretext task, and loss function aiming to learn useful general features from unlabeled data. The basic idea of most SSL baselin…
Rethinking Self-Supervised Learning Within the Framework of Partial Information Decomposition
Salman Mohamadi, Gianfranco Doretto, Donald A. Adjeroh
Self Supervised learning (SSL) has demonstrated its effectiveness in feature learning from unlabeled data. Regarding this success, there have been some arguments on the role that m…
Direct Coloring for Self-Supervised Enhanced Feature Decoupling
Salman Mohamadi, Gianfranco Doretto, Donald A. Adjeroh
The success of self-supervised learning (SSL) has been the focus of multiple recent theoretical and empirical studies, including the role of data augmentation (in feature decouplin…
FG-CXR: A Radiologist-Aligned Gaze Dataset for Enhancing Interpretability in Chest X-Ray Report Generation
Trong Thang Pham, Ngoc-Vuong Ho, Nhat-Tan Bui +8
Developing an interpretable system for generating reports in chest X-ray (CXR) analysis is becoming increasingly crucial in Computer-aided Diagnosis (CAD) systems, enabling radiolo…
TabSeq: A Framework for Deep Learning on Tabular Data via Sequential Ordering
Al Zadid Sultan Bin Habib, Kesheng Wang, Mary-Anne Hartley +2
Effective analysis of tabular data still poses a significant problem in deep learning, mainly because features in tabular datasets are often heterogeneous and have different levels…
Efficient Classification of Histopathology Images
Mohammad Iqbal Nouyed, Mary-Anne Hartley, Gianfranco Doretto +1
This work addresses how to efficiently classify challenging histopathology images, such as gigapixel whole-slide images for cancer diagnostics with image-level annotation. We use i…
TSRNet: Simple Framework for Real-time ECG Anomaly Detection with Multimodal Time and Spectrogram Restoration Network
Nhat-Tan Bui, Dinh-Hieu Hoang, Thinh Phan +4
The electrocardiogram (ECG) is a valuable signal used to assess various aspects of heart health, such as heart rate and rhythm. It plays a crucial role in identifying cardiac condi…
Heteroskedasticity as a Signature of Association for Age-Related Genes
Salman Mohamadi, Donald A. Adjeroh
Human aging is a process controlled by both genetics and environment. Many studies have been conducted to identify a subset of genes related to aging from the human genome. Biologi…
ZEETAD: Adapting Pretrained Vision-Language Model for Zero-Shot End-to-End Temporal Action Detection
Thinh Phan, Khoa Vo, Duy Le +3
Temporal action detection (TAD) involves the localization and classification of action instances within untrimmed videos. While standard TAD follows fully supervised learning with…
SAM3D: Segment Anything Model in Volumetric Medical Images
Nhat-Tan Bui, Dinh-Hieu Hoang, Minh-Triet Tran +5
Image segmentation remains a pivotal component in medical image analysis, aiding in the extraction of critical information for precise diagnostic practices. With the advent of deep…
Distributionally Robust Cross Subject EEG Decoding
Tiehang Duan, Zhenyi Wang, Gianfranco Doretto +3
Recently, deep learning has shown to be effective for Electroencephalography (EEG) decoding tasks. Yet, its performance can be negatively influenced by two key factors: 1) the high…
ChatGPT in the Age of Generative AI and Large Language Models: A Concise Survey
Salman Mohamadi, Ghulam Mujtaba, Ngan Le +2
ChatGPT is a large language model (LLM) created by OpenAI that has been carefully trained on a large amount of data. It has revolutionized the field of natural language processing…
More Synergy, Less Redundancy: Exploiting Joint Mutual Information for Self-Supervised Learning
Salman Mohamadi, Gianfranco Doretto, Donald A. Adjeroh
Self-supervised learning (SSL) is now a serious competitor for supervised learning, even though it does not require data annotation. Several baselines have attempted to make SSL mo…
A Robust Likelihood Model for Novelty Detection
Ranya Almohsen, Shivang Patel, Donald A. Adjeroh +1
Current approaches to novelty or anomaly detection are based on deep neural networks. Despite their effectiveness, neural networks are also vulnerable to imperceptible deformations…
Z-GMOT: Zero-shot Generic Multiple Object Tracking
Kim Hoang Tran, Anh Duy Le Dinh, Tien Phat Nguyen +6
Despite recent significant progress, Multi-Object Tracking (MOT) faces limitations such as reliance on prior knowledge and predefined categories and struggles with unseen objects.…
Topic Modeling in Density Functional Theory on Citations of Condensed Matter Electronic Structure Packages
Marie Dumaz, Camila Romero-Bohorquez, Donald Adjeroh +1
With an increasing number of new scientific papers being released, it becomes harder for researchers to be aware of recent articles in their field of study. Accurately classifying…