Search
Search Results
-
Pull and concentrate: improving unsupervised semantic segmentation adaptation with cross- and intra-domain consistencies
Unsupervised domain adaptation (UDA) is an important solution for the cross-domain problem in semantic segmentation. Existing segmentation UDA...
-
Problem Management Adaptation
Incident management is the first line of defense in providing immediate relief against the disruption of services and eventual downtimes. However, by...
-
Reiterative Domain Aware Multi-target Adaptation
Multi-Target Domain Adaptation (MTDA) is a recently popular powerful setting in which a single classifier is learned for multiple unlabeled target...
-
Multi-varied Cumulative Alignment for Domain Adaptation
Domain Adaptation methods can be classified into two basic families of approaches: non-parametric and parametric. Non-parametric approaches depend...
-
Toward few-shot domain adaptation with perturbation-invariant representation and transferable prototypes
Domain adaptation (DA) for semantic segmentation aims to reduce the annotation burden for the dense pixel-level prediction task. It focuses on...
-
Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modeling
Domain adaptation (DA) aims to transfer knowledge learned from a labeled source domain to an unlabeled or a less labeled but related target domain....
-
Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-training
Monocular 3D object detection (Mono3D) has achieved unprecedented success with the advent of deep learning techniques and emerging large-scale...
-
CycDA: Unsupervised Cycle Domain Adaptation to Learn from Image to Video
Although action recognition has achieved impressive results over recent years, both collection and annotation of video training data are still...
-
Generative Domain Adaptation for Face Anti-Spoofing
Face anti-spoofing (FAS) approaches based on unsupervised domain adaption (UDA) have drawn growing attention due to promising performances for target...
-
Systematic adaptation and investigation of the understandability of a formal pattern language
Formal pattern languages are used in industry to communicate and analyse requirements, as they are said to be both machine-readable and intuitively...
-
Unsupervised Domain Adaptation for Semantic Segmentation with Global and Local Consistency
Unsupervised domain adaptation(UDA) for semantic segmentation aims to learn from labeled synthetic data to segment the unlabeled real data. Many...
-
Delving into Local Features for Open-Set Domain Adaptation in Fundus Image Analysis
Unsupervised domain adaptation (UDA) has received significant attention in medical image analysis when labels are only available for the source...
-
Refined dense face alignment through image matching
Face alignment is the foundation of building 3D avatars for virtue communication in the metaverse, human-computer interaction, AI-generated content,...
-
Improving Test-Time Adaptation Via Shift-Agnostic Weight Regularization and Nearest Source Prototypes
This paper proposes a novel test-time adaptation strategy that adjusts the model pre-trained on the source domain using only unlabeled online data...
-
Smartwatch Sleep-Tracking Services Precision Evaluation Using Supervised Domain Adaptation
In 2021 a 6-week clinical pilot was deployed to evaluate the effect of the Therapeutic Horse Riding Treatment (THRT) on the state of health of the...
-
Web User Interface Adaptation for Low Vision People: An Exploratory Study Based on a Grounded Theory Review Method
People with visual impairments (PVI) are characterized as a diverse population of users due to multiple vision impairments like visual acuity, light...
-
Comparison of Semi- and Un-Supervised Domain Adaptation Methods for Whole-Heart Segmentation
Quantification of heart geometry is important in the clinical diagnosis of cardiovascular diseases. Changes in geometry are indicative of remodelling...
-
A deep learning approach to satellite image time series coregistration through alignment of road networks
The adverse effects of thawing permafrost on transportation infrastructure in northern regions are exacerbated by climate change. To address this...
-
How to gain control and influence algorithms: contesting AI to find relevant reasons
Relevancy is a prevalent term in value alignment. We either need to keep track of the relevant moral reasons, we need to embed the relevant values,...
-
Super-Focus: Domain Adaptation for Embryo Imaging via Self-supervised Focal Plane Regression
In recent years, the field of embryo imaging has seen an influx of work using machine learning. These works take advantage of large microscopy...