Search Results for author: Naji Khosravan

Found 16 papers, 4 papers with code

Multi-Modal Federated Learning for Cancer Staging over Non-IID Datasets with Unbalanced Modalities

1 code implementation7 Jan 2024 Kasra Borazjani, Naji Khosravan, Leslie Ying, Seyyedali Hosseinalipour

Given the frequent presence of diverse data modalities within patient records, leveraging FL in a multi-modal learning framework holds considerable promise for cancer staging.

Federated Learning

iBARLE: imBalance-Aware Room Layout Estimation

no code implementations29 Aug 2023 Taotao Jing, Lichen Wang, Naji Khosravan, Zhiqiang Wan, Zachary Bessinger, Zhengming Ding, Sing Bing Kang

iBARLE consists of (1) Appearance Variation Generation (AVG) module, which promotes visual appearance domain generalization, (2) Complex Structure Mix-up (CSMix) module, which enhances generalizability w. r. t.

Avg Domain Generalization +1

Graph-CoVis: GNN-based Multi-view Panorama Global Pose Estimation

no code implementations26 Apr 2023 Negar Nejatishahidin, Will Hutchcroft, Manjunath Narayana, Ivaylo Boyadzhiev, Yuguang Li, Naji Khosravan, Jana Kosecka, Sing Bing Kang

In this paper, we address the problem of wide-baseline camera pose estimation from a group of 360$^\circ$ panoramas under upright-camera assumption.

Pose Estimation

LASER: LAtent SpacE Rendering for 2D Visual Localization

1 code implementation CVPR 2022 Zhixiang Min, Naji Khosravan, Zachary Bessinger, Manjunath Narayana, Sing Bing Kang, Enrique Dunn, Ivaylo Boyadzhiev

LASER introduces the concept of latent space rendering, where 2D pose hypotheses on the floor map are directly rendered into a geometrically-structured latent space by aggregating viewing ray features.

Indoor Localization Metric Learning +1

Deformable Capsules for Object Detection

no code implementations11 Apr 2021 Rodney LaLonde, Naji Khosravan, Ulas Bagci

In this study, we introduce a new family of capsule networks, deformable capsules (DeformCaps), to address a very important problem in computer vision: object detection.

Computational Efficiency Object +2

Cross-modality Knowledge Transfer for Prostate Segmentation from CT Scans

no code implementations26 Aug 2019 Yucheng Liu, Naji Khosravan, Yulin Liu, Joseph Stember, Jonathan Shoag, Christopher E. Barbieri, Ulas Bagci, Sachin Jambawalikar

By using SynCT images (without segmentation labels) and MR images (with segmentation labels available), we have trained a deep segmentation network for precise delineation of prostate from real CT scans.

Image Segmentation Medical Image Segmentation +4

Weakly Supervised Segmentation by A Deep Geodesic Prior

no code implementations18 Aug 2019 Aliasghar Mortazi, Naji Khosravan, Drew A. Torigian, Sila Kurugol, Ulas Bagci

To alleviate this limitation, in this study, we propose a weakly supervised image segmentation method based on a deep geodesic prior.

Image Segmentation Segmentation +2

PAN: Projective Adversarial Network for Medical Image Segmentation

no code implementations11 Jun 2019 Naji Khosravan, Aliasghar Mortazi, Michael Wallace, Ulas Bagci

Adversarial learning has been proven to be effective for capturing long-range and high-level label consistencies in semantic segmentation.

Image Segmentation Pancreas Segmentation +2

On Attention Modules for Audio-Visual Synchronization

no code implementations14 Dec 2018 Naji Khosravan, Shervin Ardeshir, Rohit Puri

To judge whether audio and video signals of a multimedia presentation are synchronized, we as humans often pay close attention to discriminative spatio-temporal blocks of the video (e. g. synchronizing the lip movement with the utterance of words, or the sound of a bouncing ball at the moment it hits the ground).

Audio-Visual Synchronization

S4ND: Single-Shot Single-Scale Lung Nodule Detection

no code implementations6 May 2018 Naji Khosravan, Ulas Bagci

Our approach uses a single feed forward pass of a single network for detection and provides better performance when compared to the current literature.

Lung Nodule Detection object-detection +1

Semi-supervised multi-task learning for lung cancer diagnosis

no code implementations17 Feb 2018 Naji Khosravan, Ulas Bagci

This study set out to test the hypothesis that joint learning of false positive (FP) nodule reduction and nodule segmentation can improve the computer aided diagnosis (CAD) systems' performance on both tasks.

Lung Cancer Diagnosis Multi-Task Learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.