22 citations · 50 across the 19 of their papers we have counts for
23 papers
BLEND: Balancing Personalization vs. Generalization in Federated Vision-Language Models
Payam Abdisarabshali, Fardis Nadimi, Kasra Borazjani +3
Federated vision-language models (FedVLMs) represent one of the emerging frontiers of machine learning, aiming to integrate federated learning within the fine-tuning pipelines of v…
Bringing Multi-Modal Multi-Task Federated Foundation Models to Education Domain: Prospects and Challenges
Kasra Borazjani, Naji Khosravan, Rajeev Sahay +2
Multi-modal multi-task (M3T) foundation models (FMs) have recently shown transformative potential in artificial intelligence, with emerging applications in education. However, thei…
Hierarchical Federated Foundation Models over Wireless Networks for Multi-Modal Multi-Task Intelligence: Integration of Edge Learning with D2D/P2P-Enabled Fog Learning Architectures
Payam Abdisarabshali, Fardis Nadimi, Kasra Borazjani +6
The rise of foundation models (FMs) has reshaped the landscape of machine learning. As these models continued to grow, leveraging geo-distributed data from wireless devices has bec…
Multi-Modal Multi-Task (M3T) Federated Foundation Models for Embodied AI: Potentials and Challenges for Edge Integration
Kasra Borazjani, Payam Abdisarabshali, Fardis Nadimi +5
As embodied AI systems become increasingly multi-modal, personalized, and interactive, they must learn effectively from diverse sensory inputs, adapt continually to user preference…
Redefining non-IID Data in Federated Learning for Computer Vision Tasks: Migrating from Labels to Embeddings for Task-Specific Data Distributions
Kasra Borazjani, Payam Abdisarabshali, Naji Khosravan +1
Federated Learning (FL) has emerged as one of the prominent paradigms for distributed machine learning (ML). However, it is well-established that its performance can degrade signif…
ReStyle3D: Scene-Level Appearance Transfer with Semantic Correspondences
Liyuan Zhu, Shengqu Cai, Shengyu Huang +3
We introduce ReStyle3D, a novel framework for scene-level appearance transfer from a single style image to a real-world scene represented by multiple views. The method combines exp…
Unsupervised Federated Optimization at the Edge: D2D-Enabled Learning without Labels
Satyavrat Wagle, Seyyedali Hosseinalipour, Naji Khosravan +1
Federated learning (FL) is a popular solution for distributed machine learning (ML). While FL has traditionally been studied for supervised ML tasks, in many applications, it is im…
Multi-Modal Federated Learning for Cancer Staging over Non-IID Datasets with Unbalanced Modalities
Kasra Borazjani, Naji Khosravan, Leslie Ying +1
The use of machine learning (ML) for cancer staging through medical image analysis has gained substantial interest across medical disciplines. When accompanied by the innovative fe…
iBARLE: imBalance-Aware Room Layout Estimation
Taotao Jing, Lichen Wang, Naji Khosravan +4
Room layout estimation predicts layouts from a single panorama. It requires datasets with large-scale and diverse room shapes to train the models. However, there are significant im…
Graph-CoVis: GNN-based Multi-view Panorama Global Pose Estimation
Negar Nejatishahidin, Will Hutchcroft, Manjunath Narayana +5
In this paper, we address the problem of wide-baseline camera pose estimation from a group of 360 panoramas under upright-camera assumption. Recent work has demonstrated th…
Embedding Alignment for Unsupervised Federated Learning via Smart Data Exchange
Satyavrat Wagle, Seyyedali Hosseinalipour, Naji Khosravan +2
Federated learning (FL) has been recognized as one of the most promising solutions for distributed machine learning (ML). In most of the current literature, FL has been studied for…
Generating Topological Structure of Floorplans from Room Attributes
Yin Yu, Hutchcroft Will, Khosravan Naji +3
Analysis of indoor spaces requires topological information. In this paper, we propose to extract topological information from room attributes using what we call Iterative and adapt…
LASER: LAtent SpacE Rendering for 2D Visual Localization
Zhixiang Min, Naji Khosravan, Zachary Bessinger +4
We present LASER, an image-based Monte Carlo Localization (MCL) framework for 2D floor maps. LASER introduces the concept of latent space rendering, where 2D pose hypotheses on the…
Deformable Capsules for Object Detection
Rodney Lalonde, Naji Khosravan, Ulas Bagci
Capsule networks promise significant benefits over convolutional networks by storing stronger internal representations, and routing information based on the agreement between inter…
The International Workshop on Osteoarthritis Imaging Knee MRI Segmentation Challenge: A Multi-Institute Evaluation and Analysis Framework on a Standardized Dataset
Arjun D. Desai, Francesco Caliva, Claudia Iriondo +26
Purpose: To organize a knee MRI segmentation challenge for characterizing the semantic and clinical efficacy of automatic segmentation methods relevant for monitoring osteoarthriti…
Cross-modality Knowledge Transfer for Prostate Segmentation from CT Scans
Yucheng Liu, Naji Khosravan, Yulin Liu +5
Creating large scale high-quality annotations is a known challenge in medical imaging. In this work, based on the CycleGAN algorithm, we propose leveraging annotations from one mod…
Weakly Supervised Segmentation by A Deep Geodesic Prior
Aliasghar Mortazi, Naji Khosravan, Drew A. Torigian +2
The performance of the state-of-the-art image segmentation methods heavily relies on the high-quality annotations, which are not easily affordable, particularly for medical data. T…
PAN: Projective Adversarial Network for Medical Image Segmentation
Naji Khosravan, Aliasghar Mortazi, Michael Wallace +1
Adversarial learning has been proven to be effective for capturing long-range and high-level label consistencies in semantic segmentation. Unique to medical imaging, capturing 3D s…
On Attention Modules for Audio-Visual Synchronization
Naji Khosravan, Shervin Ardeshir, Rohit Puri
With the development of media and networking technologies, multimedia applications ranging from feature presentation in a cinema setting to video on demand to interactive video con…
S4ND: Single-Shot Single-Scale Lung Nodule Detection
Naji Khosravan, Ulas Bagci
The state of the art lung nodule detection studies rely on computationally expensive multi-stage frameworks to detect nodules from CT scans. To address this computational challenge…
A Collaborative Computer Aided Diagnosis (C-CAD) System with Eye-Tracking, Sparse Attentional Model, and Deep Learning
Naji Khosravan, Haydar Celik, Baris Turkbey +3
There are at least two categories of errors in radiology screening that can lead to suboptimal diagnostic decisions and interventions:(i)human fallibility and (ii)complexity of vis…
Semi-supervised multi-task learning for lung cancer diagnosis
Naji Khosravan, Ulas Bagci
Early detection of lung nodules is of great importance in lung cancer screening. Existing research recognizes the critical role played by CAD systems in early detection and diagnos…
Gaze2Segment: A Pilot Study for Integrating Eye-Tracking Technology into Medical Image Segmentation
Naji Khosravan, Haydar Celik, Baris Turkbey +9
This study introduced a novel system, called Gaze2Segment, integrating biological and computer vision techniques to support radiologists' reading experience with an automatic image…