Filters








4 Hits in 6.5 sec

AUGCO: Augmentation Consistency-guided Self-training for Source-free Domain Adaptive Semantic Segmentation [article]

Viraj Prabhu, Shivam Khare, Deeksha Kartik, Judy Hoffman
<span title="2022-01-06">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We focus on source-free domain adaptation for semantic segmentation, wherein a source model must adapt itself to a new target domain given only unlabeled target data.  ...  Most modern approaches for domain adaptive semantic segmentation rely on continued access to source data during adaptation, which may be infeasible due to computational or privacy constraints.  ...  We thank Prithvijit Chattopadhyay for feedback on the draft. This work was supported in part by funding from the DARPA LwLL project.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.10140v2">arXiv:2107.10140v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ligkvixukfbojdafzor6vxuydy">fatcat:ligkvixukfbojdafzor6vxuydy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210725132635/https://arxiv.org/pdf/2107.10140v1.pdf" title="fulltext PDF download [not primary version]" 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] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/59/cd/59cdeeae114ffecedcca15fdd0f384dff6cee520.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.10140v2" 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>

Domain Adaptive Semantic Segmentation without Source Data: Align, Teach and Propagate [article]

Yuxi Wang and Jian Liang and Jun Xiao and Yuran Yang and Shuqi Mei and Zhaoxiang Zhang
<span title="2021-12-14">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To tackle this problem, we focus on an interesting and challenging cross-domain semantic segmentation task where only the trained source model is provided to the target domain.  ...  To mitigate the domain gap, previous cross-domain semantic segmentation methods always assume the co-existence of source data and target data during domain alignment.  ...  Conclusion This paper presents a novel source data-free framework for domain adaptive semantic segmentation called ATP.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.11653v3">arXiv:2106.11653v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/y26qe5aqzng3dp5koskpwy7dfy">fatcat:y26qe5aqzng3dp5koskpwy7dfy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211216212330/https://arxiv.org/pdf/2106.11653v3.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/13/56/135681b42f5cd3fb8fd01930a4f22d45fd654553.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.11653v3" 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>

DistillAdapt: Source-Free Active Visual Domain Adaptation [article]

Divya Kothandaraman, Sumit Shekhar, Abhilasha Sancheti, Manoj Ghuhan, Tripti Shukla, Dinesh Manocha
<span title="2022-05-24">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We present a novel method, DistillAdapt, for the challenging problem of Source-Free Active Domain Adaptation (SF-ADA).  ...  source data for adaptation.  ...  DistillAdapt For Source-Free Active Domain Adaptation (SF-ADA), we assume (i) a network, N S , pre-trained on a source-domain, S (the source data is not available for adaptation) and (ii) an unlabeled  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.12840v1">arXiv:2205.12840v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ct2hgy3tlfcvlox7t5pd3ovnl4">fatcat:ct2hgy3tlfcvlox7t5pd3ovnl4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220527033625/https://arxiv.org/pdf/2205.12840v1.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/3c/e0/3ce07a3a93030afecc10507186f141bf340eb13c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.12840v1" 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>

A Survey of Outlier Detection Techniques in IoT: Review and Classification

Mustafa Al Samara, Ismail Bennis, Abdelhafid Abouaissa, Pascal Lorenz
<span title="2022-01-04">2022</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/bajb2sq2z5a3beaybwby4ac4w4" style="color: black;">Journal of Sensor and Actuator Networks</a> </i> &nbsp;
In this context, one of the main issues requiring more research and adapted solutions is the outlier detection problem.  ...  Finally, a comparative study for these techniques is provided.  ...  Firstly, they used the data gathered from the sensors by the S4T for training the algorithm by using two neural networks autoencoders.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/jsan11010004">doi:10.3390/jsan11010004</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5b2h43grsrewxdtag3ezgtjjle">fatcat:5b2h43grsrewxdtag3ezgtjjle</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220503223904/https://mdpi-res.com/d_attachment/jsan/jsan-11-00004/article_deploy/jsan-11-00004.pdf?version=1641288428" 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/b3/9a/b39a14cf407358e8d0f524953f7f625910d23125.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/jsan11010004"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>