Filters








8,966 Hits in 6.7 sec

Adapting Off-the-Shelf Source Segmenter for Target Medical Image Segmentation [article]

Xiaofeng Liu, Fangxu Xing, Chao Yang, Georges El Fakhri, Jonghye Woo
<span title="2021-06-23">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To alleviate this, in this work, we target source free UDA for segmentation, and propose to adapt an "off-the-shelf" segmentation model pre-trained in the source domain to the target domain, with an adaptive  ...  Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a labeled source domain to an unlabeled and unseen target domain, which is usually trained on data from both domains.  ...  We minimize the domain discrepancy based on the adaptively computed batch-wise statistics in each channel.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.12497v1">arXiv:2106.12497v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/veavv5vu6fag7jq3bkqdurj4qm">fatcat:veavv5vu6fag7jq3bkqdurj4qm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210625142911/https://arxiv.org/pdf/2106.12497v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/35/da/35da245cf450b128f4d0e5cc96a93060897141a0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.12497v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Unsupervised Domain Adaptation for Cardiac Segmentation: Towards Structure Mutual Information Maximization [article]

Changjie Lu, Shen Zheng, Gaurav Gupta
<span title="2022-04-20">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Unsupervised domain adaptation approaches have recently succeeded in various medical image segmentation tasks.  ...  This paper introduces UDA-VAE++, an unsupervised domain adaptation framework for cardiac segmentation with a compact loss function lower bound.  ...  Related Work Unsupervised Domain Adaptation Unsupervised Domain Adaptation (UDA) has been widely used for biomedical image segmentation tasks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.09334v1">arXiv:2204.09334v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bbmyxgsbbbf7fd4cc7wkxgeamq">fatcat:bbmyxgsbbbf7fd4cc7wkxgeamq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220423232344/https://arxiv.org/pdf/2204.09334v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ca/3c/ca3c973c12def27aa19c5d20bc818f46d71bbc7e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.09334v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Source-free unsupervised domain adaptation for cross-modality abdominal multi-organ segmentation [article]

Jin Hong, Yu-Dong Zhang, Weitian Chen
<span title="2022-05-28">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Furthermore, the proposed approach is proven to be effective for source-free unsupervised domain adaptation in reverse direction.  ...  In the first stage, the feature map statistics-guided model adaptation combined with entropy minimization is developed to help the top segmentation network reliably segment the target images.  ...  In the medical image analysis field, Chen et al. (2021) proposed a denoised pseudo-labeling strategy for source-free unsupervised domain adaptation in fundus image segmentation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.12221v4">arXiv:2111.12221v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/medqgshumfdijbesm6kzzyyche">fatcat:medqgshumfdijbesm6kzzyyche</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220610090120/https://arxiv.org/ftp/arxiv/papers/2111/2111.12221.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/39/40/394096d620ce78bf433db01d0ca71a9dacd9eb6f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.12221v4" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Adversarial Semantic Hallucination for Domain Generalized Semantic Segmentation [article]

Gabriel Tjio, Ping Liu, Joey Tianyi Zhou, Rick Siow Mong Goh
<span title="2021-10-26">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
the segmentation probability maps of the source domain image.  ...  Consequently, there is a need for methods that generalize well despite restricted access to target domain data during training.  ...  Unsupervised Domain Adaptation Unsupervised domain adaptation (UDA) is a subset of transfer learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.04144v6">arXiv:2106.04144v6</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vwags36rhre65hyr6jrg2w3zim">fatcat:vwags36rhre65hyr6jrg2w3zim</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211031222517/https://arxiv.org/pdf/2106.04144v6.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/22/c5/22c53a52c54cbd5238ac7e0cca057b236ef6d7b9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.04144v6" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Tune it the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Density [article]

Kuniaki Saito, Donghyun Kim, Piotr Teterwak, Stan Sclaroff, Trevor Darrell, Kate Saenko
<span title="2021-08-24">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Unsupervised domain adaptation (UDA) methods can dramatically improve generalization on unlabeled target domains.  ...  Our criterion is simpler than competing validation methods, yet more effective; it can tune hyper-parameters and the number of training iterations in both image classification and semantic segmentation  ...  Empirically, we observe that SND works well for closed and partial domain adaptive image classification, as well as for domain adaptive semantic segmentation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.10860v1">arXiv:2108.10860v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kewgg2j67bg3zlkmz54bzv4zr4">fatcat:kewgg2j67bg3zlkmz54bzv4zr4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210829192037/https://arxiv.org/pdf/2108.10860v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e0/c9/e0c9464d69ad1a54450e0ba20c7c7fd95806b828.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.10860v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation [article]

Judy Hoffman, Dequan Wang, Fisher Yu, Trevor Darrell
<span title="2016-12-08">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we introduce the first domain adaptive semantic segmentation method, proposing an unsupervised adversarial approach to pixel prediction problems.  ...  Global domain alignment is performed using a novel semantic segmentation network with fully convolutional domain adversarial learning.  ...  In this work, we propose the first unsupervised domain adaptation method for transferring semantic segmentation FCNs across image domains.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1612.02649v1">arXiv:1612.02649v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3ku35eodhvcwxpboh4hrggnq3y">fatcat:3ku35eodhvcwxpboh4hrggnq3y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200927110221/https://arxiv.org/pdf/1612.02649v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/95/bc/95bc6f4ff5033a091b6ddc6a4290a58c7e6ddc66.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1612.02649v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Unsupervised Domain Adaptation for Retinal Vessel Segmentation with Adversarial Learning and Transfer Normalization [article]

Wei Feng, Lie Ju, Lin Wang, Kaimin Song, Xin Wang, Xin Zhao, Qingyi Tao, Zongyuan Ge
<span title="2021-08-04">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we explore unsupervised domain adaptation in retinal vessel segmentation by using entropy-based adversarial learning and transfer normalization layer to train a segmentation network, which  ...  minimization on the target domain.  ...  Fig. 2 . 2 The overview of our proposed framework for unsupervised domain adaptation in retinal vessel segmentation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.01821v1">arXiv:2108.01821v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/h4ju5huljjd6pfebi3aylfcnnq">fatcat:h4ju5huljjd6pfebi3aylfcnnq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210806081457/https://arxiv.org/pdf/2108.01821v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/9a/54/9a544e17ac64bb15cca9b9cabb1b425bffe166e7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.01821v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Fully Convolutional Adaptation Networks for Semantic Segmentation [article]

Yiheng Zhang and Zhaofan Qiu and Ting Yao and Dong Liu and Tao Mei
<span title="2018-04-23">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The former adapts source-domain images to appear as if drawn from the "style" in the target domain and the latter attempts to learn domain-invariant representations.  ...  Specifically, we present Fully Convolutional Adaptation Networks (FCAN), a novel deep architecture for semantic segmentation which combines Appearance Adaptation Networks (AAN) and Representation Adaptation  ...  In short, our work in this paper mainly focuses on unsupervised adaptation for semantic segmentation task, which is seldom investigated.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1804.08286v1">arXiv:1804.08286v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lloyxytcjbf53pyfd6wahdy3be">fatcat:lloyxytcjbf53pyfd6wahdy3be</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200906183456/https://arxiv.org/pdf/1804.08286v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/94/57/9457e4bc712552bb15faa639a504ec6afdc91c84.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1804.08286v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Fully Convolutional Adaptation Networks for Semantic Segmentation

Yiheng Zhang, Zhaofan Qiu, Ting Yao, Dong Liu, Tao Mei
<span title="">2018</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition</a> </i> &nbsp;
The former adapts source-domain images to appear as if drawn from the "style" in the target domain and the latter attempts to learn domain-invariant represen- tations.  ...  Specifically, we present Fully Convolutional Adaptation Networks (FCAN), a novel deep architecture for semantic segmentation which combines Appearance Adaptation Networks (AAN) and Representation Adaptation  ...  In short, our work in this paper mainly focuses on unsupervised adaptation for semantic segmentation task, which is seldom investigated.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2018.00712">doi:10.1109/cvpr.2018.00712</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/ZhangQY0M18.html">dblp:conf/cvpr/ZhangQY0M18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4eglnrslv5gqtnjwntmtj3xguq">fatcat:4eglnrslv5gqtnjwntmtj3xguq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190819040023/http://openaccess.thecvf.com:80/content_cvpr_2018/papers/Zhang_Fully_Convolutional_Adaptation_CVPR_2018_paper.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/3a/39/3a39e73323c97aa50887883823716f5e965c2abd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2018.00712"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Unsupervised Domain Adaptation with Implicit Pseudo Supervision for Semantic Segmentation [article]

Wanyu Xu, Zengmao Wang, Wei Bian
<span title="2022-04-14">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Pseudo-labelling is a popular technique in unsuper-vised domain adaptation for semantic segmentation.  ...  To further implicitly utilize the pseudo labels, we maximize the distances of features for different classes and minimize the distances for the same classes by triplet loss.  ...  ACKNOWLEDGMENT Sincere gratitude to anonymous reviewers for careful work and considerate suggestions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.06747v1">arXiv:2204.06747v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ppbqvvgkifedhkhnqexswdzcky">fatcat:ppbqvvgkifedhkhnqexswdzcky</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220521010835/https://arxiv.org/pdf/2204.06747v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e8/05/e805e56f6b2d3eb85ddc2678ffe3b6b7f9da8083.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.06747v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Towards Adaptive Semantic Segmentation by Progressive Feature Refinement [article]

Bin Zhang, Shengjie Zhao, Rongqing Zhang
<span title="2020-09-30">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Unsupervised adaptive semantic segmentation aims to obtain a robust classifier trained with source domain data, which is able to maintain stable performance when deployed to a target domain with different  ...  As a result, the segmentation models trained with source domain images can be transferred to a target domain without significant performance degradation.  ...  Unsupervised domain adaptation offers a formal framework for addressing the above-mentioned issues by bridging the domain gap between the source and target domains.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.14420v1">arXiv:2009.14420v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/43g4romqz5bnrf6fbiwht7ahke">fatcat:43g4romqz5bnrf6fbiwht7ahke</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201008085324/https://arxiv.org/pdf/2009.14420v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.14420v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation [article]

Zhedong Zheng, Yi Yang
<span title="2020-10-15">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper focuses on the unsupervised domain adaptation of transferring the knowledge from the source domain to the target domain in the context of semantic segmentation.  ...  To overcome the problem, this paper proposes to explicitly estimate the prediction uncertainty during training to rectify the pseudo label learning for unsupervised semantic segmentation adaptation.  ...  In unsupervised semantic segmentation adaptation, two datasets collected in different environments are considered: a labeled source-domain dataset where category labels are provided for every pixel, and  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.03773v3">arXiv:2003.03773v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4kmdd7v6tnbphabogx3cfrt6fq">fatcat:4kmdd7v6tnbphabogx3cfrt6fq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201017000733/https://arxiv.org/pdf/2003.03773v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.03773v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Dispensed Transformer Network for Unsupervised Domain Adaptation [article]

Yunxiang Li, Jingxiong Li, Ruilong Dan, Shuai Wang, Kai Jin, Guodong Zeng, Jun Wang, Xiangji Pan, Qianni Zhang, Huiyu Zhou, Qun Jin, Li Wang (+1 others)
<span title="2021-10-28">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To mitigate this problem, a novel unsupervised domain adaptation (UDA) method named dispensed Transformer network (DTNet) is introduced in this paper. Our novel DTNet contains three modules.  ...  Accurate segmentation is a crucial step in medical image analysis and applying supervised machine learning to segment the organs or lesions has been substantiated effective.  ...  This research mainly involves three fields: medical image segmentation, unsupervised domain adaptation, and transformer in vision.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.14944v1">arXiv:2110.14944v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/khwdtqdxanftnka64q563ibl74">fatcat:khwdtqdxanftnka64q563ibl74</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211030230309/https://arxiv.org/pdf/2110.14944v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c6/48/c6481af1c5ebba68a8f59ade7d07eab1265d8e15.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.14944v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Exploiting Negative Learning for Implicit Pseudo Label Rectification in Source-Free Domain Adaptive Semantic Segmentation [article]

Xin Luo, Wei Chen, Yusong Tan, Chen Li, Yulin He, Xiaogang Jia
<span title="2021-06-23">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Extensive experiments have been performed on domain adaptive semantic segmentation benchmark, GTA5 → Cityscapes.  ...  Aiming at these pitfalls, this study develops a domain adaptive solution to semantic segmentation with pseudo label rectification (namely PR-SFDA), which operates in two phases: 1) Confidence-regularized  ...  Self-training for Domain Adaptive Segmentation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.12123v1">arXiv:2106.12123v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tgxeuol4vfbbvdbaorrej4nqsm">fatcat:tgxeuol4vfbbvdbaorrej4nqsm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210625122959/https://arxiv.org/pdf/2106.12123v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/7d/51/7d517abb6deba60c148552f3e71f1d0ea9d3b30f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.12123v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Unsupervised Domain Adaptation for LiDAR Panoptic Segmentation [article]

Borna Bešić, Nikhil Gosala, Daniele Cattaneo, Abhinav Valada
<span title="2021-09-30">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Unsupervised Domain Adaptation (UDA) techniques are thus essential to fill this domain gap and retain the performance of models on new sensor setups without the need for additional data labeling.  ...  In this paper, we propose AdaptLPS, a novel UDA approach for LiDAR panoptic segmentation that leverages task-specific knowledge and accounts for variation in the number of scan lines, mounting position  ...  CONCLUSION In this paper, we present the first end-to-end trainable unsupervised domain adaptation approach for LiDAR panoptic segmentation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.15286v1">arXiv:2109.15286v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ctn7spzbejcpldzrd7sbwhnm44">fatcat:ctn7spzbejcpldzrd7sbwhnm44</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211008111126/https://arxiv.org/pdf/2109.15286v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/55/8e/558e9cc59a15182a8356eeaef43e7c57bf500d36.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.15286v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 8,966 results