A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Filters
Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency
[article]
2021
arXiv
pre-print
Preserved Fulltext
Other Versions
To address this challenge, we study a more realistic setting, unsupervised 3D domain adaptive detection, which only utilizes source domain annotations. 1) We first comprehensively investigate the major ...
Our key insight is that geometric mismatch is the key factor of domain shift. 2) Then, we propose a novel and unified framework, Multi-Level Consistency Network (MLC-Net), which employs a teacher-student ...
MLC-Net achieves two major design goals towards effective unsupervised 3D domain adaptive detection. ...
arXiv:2107.11355v2
fatcat:55o6pvwqtndbvgjvjwov63cilq
Unsupervised Subcategory Domain Adaptive Network for 3D Object Detection in LiDAR
2021
Electronics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Our object detection adaptive network consists of a general object detection network, a global feature adaptation network, and a special subcategory instance adaptation network. ...
In this paper, we propose a method for object detection using an unsupervised adaptive network, which does not require additional annotation data of the target domain. ...
In this paper, we propose a novel unsupervised domain adaptation method for 3D object detection. The proposed approach combines global adaptation with local multiple subcategory adaptation. ...
doi:10.3390/electronics10080927
fatcat:77x323rmmrbpzfg2joophmb27u
Unsupervised Domain Adaptation Learning for Hierarchical Infant Pose Recognition with Synthetic Data
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
The model consists of an image branch and a pose branch, which respectively generates the coarse-level logits facilitated by the unsupervised domain adaptation and the 3D keypoints using the HRNet with ...
However, this domain mismatch between real and synthetic training samples often leads to performance degradation during inference. ...
Unsupervised Domain Adaptation Various works have been targeting domain adaptation to overcome the domain shift problems. Sener et al. ...
arXiv:2205.01892v1
fatcat:toseazbevvg4dbqxdaclzv47fy
Advancing Medical Imaging Informatics by Deep Learning-Based Domain Adaptation
2020
IMIA Yearbook of Medical Informatics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Domain adaptation (DA) has been developed to transfer the knowledge from a labeled data domain to a related but unlabeled domain in either image space or feature space. ...
Opportunities include domain transferability, multi-modal DA, and applications that benefit from synthetic data. ...
CycleGAN has been expanded to handle larger domain shifts with semantic-consistency loss functions (CyCADA [35] ), multi-domain translation (StarGAN [49] ), and translation between two domains with multi-modal ...
doi:10.1055/s-0040-1702009
pmid:32823306
fatcat:gtlhoh6m3fh4hcumfzdlpdohr4
UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimation
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
To tackle this problem, we propose an unsupervised domain adaptation (UDA) for category-level object pose estimation, called UDA-COPE. ...
Inspired by recent multi-modal UDA techniques, the proposed method exploits a teacher-student self-supervised learning scheme to train a pose estimation network without using target domain pose labels. ...
To compare our methods with the previous multi-modal unsupervised domain adaptation method, we also applied xMUDA [14] which constraints the 2D feature and 3D feature for consistency. xMUDA consistency ...
arXiv:2111.12580v2
fatcat:qtx2grkcavejhfeg3yuqlffokm
Learning Cascaded Detection Tasks with Weakly-Supervised Domain Adaptation
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
As our experiments demonstrate, the approach is competitive with fully supervised settings while outperforming unsupervised adaptation approaches by a large margin. ...
In this work, we propose a weakly supervised domain adaptation setting which exploits the structure of cascaded detection tasks. ...
Cross-Domain Learning with Weak Supervision: While the unsupervised regime has been extensively studied, domain adaptation with access to weak annotations from an auxiliary task in the target domain has ...
arXiv:2107.04523v1
fatcat:qqfnetb4u5dozmx4kvcghjkpg4
Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We propose a single-frame approach for source-free, unsupervised domain adaptation of lidar-based 3D object detectors that uses class prototypes to mitigate the effect pseudo-label noise. ...
3D object detection networks tend to be biased towards the data they are trained on. ...
We propose an unsupervised, source-free domain adaptation framework for 3D object detection that addresses the issue of incorrect, over-confident pseudo labels during selftraining through the use of class ...
arXiv:2111.15656v2
fatcat:6lzmcwufyzfxtni53swxkiuohi
Domain Adaptive Relational Reasoning for 3D Multi-Organ Segmentation
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this paper, we present a novel unsupervised domain adaptation (UDA) method, named Domain Adaptive Relational Reasoning (DARR), to generalize 3D multi-organ segmentation models to medical data collected ...
To guarantee the transferability of the learned spatial relationship to multiple domains, we additionally introduce two schemes: 1) Employing a super-resolution network also jointly trained with the segmentation ...
In this paper, we focus on unsupervised domain adaptation (UDA) for deviating acquisition scanners/protocols in 3D abdominal multi-organ segmentation on CT scans. ...
arXiv:2005.09120v2
fatcat:uaoaehddgffhlh3btpresyrb5y
Hierarchical Domain-Adapted Feature Learning for Video Saliency Prediction
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We provide the base hierarchical learning mechanism with two techniques for domain adaptation and domain-specific learning. ...
When, instead, we test it in an unsupervised domain adaptation setting, by enabling hierarchical gradient reversal layers, we obtain performance comparable to supervised state-of-the-art. ...
RMDN [3] processes video clips with a 3D convolutional neural network based on C3D [59] , and then employs LSTMs to enforce temporal consistency among the segments. ...
arXiv:2010.01220v4
fatcat:woawbhame5bs5kmeh6qrhshzqi
2020 Index IEEE Transactions on Image Processing Vol. 29
2020
IEEE Transactions on Image Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
., +, TIP 2020 7565-7577 Generating Target Image-Label Pairs for Unsupervised Domain Adaptation. ...
Liu, J., +, TIP 2020 7845-7860
Collaborative Unsupervised Domain Adaptation for Medical Image Diagno-
sis. ...
doi:10.1109/tip.2020.3046056
fatcat:24m6k2elprf2nfmucbjzhvzk3m
SF-UDA^3D: Source-Free Unsupervised Domain Adaptation for LiDAR-Based 3D Object Detection
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
This paper proposes SF-UDA^3D, the first Source-Free Unsupervised Domain Adaptation (SF-UDA) framework to domain-adapt the state-of-the-art PointRCNN 3D detector to target domains for which we have no ...
SF-UDA^3D outperforms both previous domain adaptation techniques based on features alignment and state-of-the-art 3D object detection methods which additionally use few-shot target annotations or target ...
Unsupervised Domain Adaptation (UDA) for 2D Object Detection. ...
arXiv:2010.08243v2
fatcat:4kbapwfjm5gv7phpekgexnnvem
Manual-Label Free 3D Detection via An Open-Source Simulator
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper, we propose a manual-label free 3D detection algorithm that leverages the CARLA simulator to generate a large amount of self-labeled training samples and introduces a novel Domain Adaptive ...
Then a DA-VoxelNet that integrates both a sample-level DA module and an anchor-level DA module is proposed to enable the detector trained by the synthetic data to adapt to real scenario. ...
Domain Adaptive VoxelNet We propose a novel unsupervised domain adaptation algorithm to further align the domain shift. ...
arXiv:2011.07784v1
fatcat:c4sjmrjyajamrkk73ami7dih3q
Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Then, we propose STMono3D, a new self-teaching framework for unsupervised domain adaptation on Mono3D. ...
Monocular 3D object detection (Mono3D) has achieved unprecedented success with the advent of deep learning techniques and emerging large-scale autonomous driving datasets. ...
We call this task unsupervised domain adaptation (UDA) for monocular 3D object detection. ...
arXiv:2204.11590v2
fatcat:oho5oi4go5fxtavavfkqeoiqme
When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey
2020
Patterns
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Transferability means that when a well-trained model is transferred to other testing domains, the accuracy is still good. ...
typical computer vision tasks in autonomous systems, including image style transfer, image super-resolution, image deblurring/dehazing/rain removal, semantic segmentation, depth estimation, pedestrian detection ...
, Hoffman et al. 74 proposed CyCADA by combining domain adaptation and cycle-consistent adversarial, which uniformly considers feature-level and pixellevel adversarial domain adaptation and cycle-consistency ...
doi:10.1016/j.patter.2020.100050
pmid:33205114
pmcid:PMC7660378
fatcat:vs7wm2yrwjamjbaml36663wvze
PnP-AdaNet: Plug-and-Play Adversarial Domain Adaptation Network at Unpaired Cross-modality Cardiac Segmentation
2019
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
The experimental results with comprehensive ablation studies have demonstrated the excellent efficacy of our proposed method for unsupervised cross-modality domain adaptation. ...
We validate our domain adaptation method on cardiac segmentation in unpaired MRI and CT, with four different anatomical structures. ...
[9] , which conducted unsupervised domain adaptation by adversarial learning in multi-level feature space for brain lesion segmentation. ...
doi:10.1109/access.2019.2929258
fatcat:u4nuxyrzvzerfbrocgg44t6k5m
« Previous
Showing results 1 — 15 out of 11,206 results