Search Results for author:
Found 19 papers, 5 papers with code
Redefining non-IID Data in Federated Learning for Computer Vision Tasks: Migrating from Labels to Embeddings for Task-Specific Data Distributions
Federated Learning (FL) represents a paradigm shift in distributed machine learning (ML), enabling clients to train models collaboratively while keeping their raw data private.
ReStyle3D: Scene-Level Appearance Transfer with Semantic Correspondences
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.
Unsupervised Federated Optimization at the Edge: D2D-Enabled Learning without Labels
Specifically, we introduce a \textit{smart information push-pull} methodology for data/embedding exchange tailored to FL settings with either soft or strict data privacy restrictions.
Multi-Modal Federated Learning for Cancer Staging over Non-IID Datasets with Unbalanced Modalities
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.
iBARLE: imBalance-Aware Room Layout Estimation
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.
Graph-CoVis: GNN-based Multi-view Panorama Global Pose Estimation
In this paper, we address the problem of wide-baseline camera pose estimation from a group of 360$^\circ$ panoramas under upright-camera assumption.
Embedding Alignment for Unsupervised Federated Learning via Smart Data Exchange
In most of the current literature, FL has been studied for supervised ML tasks, in which edge devices collect labeled data.
LASER: LAtent SpacE Rendering for 2D Visual Localization
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.
Zillow Indoor Dataset: Annotated Floor Plans With 360deg Panoramas and 3D Room Layouts
We present Zillow Indoor Dataset (ZInD): A large indoor dataset with 71, 474 panoramas from 1, 524 real unfurnished homes.
Deformable Capsules for Object Detection
In this study, we introduce a new family of capsule networks, deformable capsules (\textit{DeformCaps}), to address a very important problem in computer vision: object detection.
The International Workshop on Osteoarthritis Imaging Knee MRI Segmentation Challenge: A Multi-Institute Evaluation and Analysis Framework on a Standardized Dataset
Purpose: To organize a knee MRI segmentation challenge for characterizing the semantic and clinical efficacy of automatic segmentation methods relevant for monitoring osteoarthritis progression.
Cross-modality Knowledge Transfer for Prostate Segmentation from CT Scans
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.
Weakly Supervised Segmentation by A Deep Geodesic Prior
To alleviate this limitation, in this study, we propose a weakly supervised image segmentation method based on a deep geodesic prior.
PAN: Projective Adversarial Network for Medical Image Segmentation
Adversarial learning has been proven to be effective for capturing long-range and high-level label consistencies in semantic segmentation.
On Attention Modules for Audio-Visual Synchronization
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).
S4ND: Single-Shot Single-Scale Lung Nodule Detection
Our approach uses a single feed forward pass of a single network for detection and provides better performance when compared to the current literature.
Semi-supervised multi-task learning for lung cancer diagnosis
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.
A Collaborative Computer Aided Diagnosis (C-CAD) System with Eye-Tracking, Sparse Attentional Model, and Deep Learning
Computer aided diagnostic (CAD) tools are developed to help radiologists to compensate for some of these errors.
Gaze2Segment: A Pilot Study for Integrating Eye-Tracking Technology into Medical Image Segmentation
During diagnostic assessment of lung CT scans, the radiologists' gaze information were used to create a visual attention map.
