Filters








1,572 Hits in 5.1 sec

From ImageNet to Mining: Adapting Visual Object Detection with Minimal Supervision [chapter]

Alex Bewley, Ben Upcroft
<span title="">2016</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/lirc5icuifhy7ln5rynpn4ak2e" style="color: black;">Springer Tracts in Advanced Robotics</a> </i> &nbsp;
This paper presents visual detection and classification of light vehicles and personnel on a mine site.  ...  Our system is tested on over 10km of real mine site data and we were able to detect both light vehicles and personnel.  ...  The authors would also like to acknowledge AngloAmerican for allowing data collection at the Dawson operation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-27702-8_33">doi:10.1007/978-3-319-27702-8_33</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yg7hjxs5kndqjdugj5tkyrufty">fatcat:yg7hjxs5kndqjdugj5tkyrufty</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20150907192231/http://eprints.qut.edu.au/84152/1/CameraReadyFSR2015.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/df/30/df30d86219e87567d1a207cbd310189530c45cd2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-27702-8_33"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Rebalanced Siamese Contrastive Mining for Long-Tailed Recognition [article]

Zhisheng Zhong, Jiequan Cui, Eric Lo, Zeming Li, Jian Sun, Jiaya Jia
<span title="2022-03-22">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, at the original batch level, we introduce a class-balanced supervised contrastive loss to assign adaptive weights for different classes.  ...  We propose supervised hard positive and negative pairs mining to pick up informative pairs for contrastive computation and improve representation learning.  ...  shown great success to many visual discriminative tasks, including image recognition [19, 29] , object detection [38] , and semantic segmentation [9] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.11506v1">arXiv:2203.11506v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/q4mc6zedvvb6hnwt22fpgdhpca">fatcat:q4mc6zedvvb6hnwt22fpgdhpca</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220325212608/https://arxiv.org/pdf/2203.11506v1.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/ab/97/ab97eb4f8d1b6b296c3033b224a16bd965042a71.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.11506v1" 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>

Glo-In-One: Holistic Glomerular Detection, Segmentation, and Lesion Characterization with Large-scale Web Image Mining [article]

Tianyuan Yao, Yuzhe Lu, Jun Long, Aadarsh Jha, Zheyu Zhu, Zuhayr Asad, Haichun Yang, Agnes B. Fogo, Yuankai Huo
<span title="2022-05-31">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To leverage the performance of the Glo-In-One toolkit, we introduce self-supervised deep learning to glomerular quantification via large-scale web image mining.  ...  The quantitative detection, segmentation, and characterization of glomeruli from high-resolution whole slide imaging (WSI) play essential roles in the computer-assisted diagnosis and scientific research  ...  An Adam Optimizer was used to adaptively alter the learning rate, with beta values ranging from 0.9 to 0.999. 2) Results: From the results (Table .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2206.00123v1">arXiv:2206.00123v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6n5vp5gv35c7bd6fayndwktrme">fatcat:6n5vp5gv35c7bd6fayndwktrme</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220611092552/https://arxiv.org/pdf/2206.00123v1.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/f5/76/f5768acafb3c9d584b4eceeb84adaf884df6ad21.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2206.00123v1" 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>

Transductive Zero-Shot Hashing via Coarse-to-Fine Similarity Mining [article]

Hanjiang Lai, Yan Pan
<span title="2017-11-08">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
learn the effective common image representations, and 2) a coarse-to-fine module, which begins with finding the most representative images from target classes and then further detect similarities among  ...  We put forward a simple yet efficient joint learning approach via coarse-to-fine similarity mining which transfers knowledges from source data to target data.  ...  Fine Similarity Mining With the found m images from the unlabelled data, we need a fine stage to find the similarities among these images.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1711.02856v1">arXiv:1711.02856v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/eqwut2d64fay7bindfcu6zoi7y">fatcat:eqwut2d64fay7bindfcu6zoi7y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930043410/https://arxiv.org/pdf/1711.02856v1.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/53/9a53615f62b148c99ea9412da0b1043597c53381.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1711.02856v1" 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>

Object Discovery From a Single Unlabeled Image by Mining Frequent Itemset With Multi-scale Features [article]

Runsheng Zhang, Yaping Huang, Mengyang Pu, Jian Zhang, Qingji Guan, Qi Zou, Haibin Ling
<span title="2020-08-08">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To tackle this problem, we propose a simple but effective pattern mining-based method, called Object Location Mining (OLM), which exploits the advantages of data mining and feature representation of pre-trained  ...  We also evaluate our approach compared with unsupervised saliency detection methods and achieves competitive results on seven benchmark datasets.  ...  [53] solves the pixel-wise segmentation task as an energy minimization problem. The other branch of salency detection is supervised methods, which need pixel-level labels for training.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1902.09968v3">arXiv:1902.09968v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2col2budbjgzjoykscdl632qv4">fatcat:2col2budbjgzjoykscdl632qv4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200812051304/https://arxiv.org/pdf/1902.09968v3.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/3b/b7/3bb790ae323604ac0f242dcb210bfaef75562029.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1902.09968v3" 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>

Mining Latent Classes for Few-shot Segmentation [article]

Lihe Yang, Wei Zhuo, Lei Qi, Yinghuan Shi, Yang Gao
<span title="2021-09-27">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Based on conventional episodic training on support-query pairs, we add an additional mining branch that exploits latent novel classes via transferable sub-clusters, and a new rectification technique on  ...  both background and foreground categories to enforce more stable prototypes.  ...  Motivated by this, we boost the few-shot segmentation via mining latent objects from the backgrounds. Semi-/self-supervised Learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.15402v3">arXiv:2103.15402v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zksnaw3pqnaj5boieyqpdf6vsm">fatcat:zksnaw3pqnaj5boieyqpdf6vsm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210929143316/https://arxiv.org/pdf/2103.15402v3.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/1f/6a/1f6a771d44ade285d8b6508b85848d6d06fa1dc8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.15402v3" 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>

ATOM: Robustifying Out-of-distribution Detection Using Outlier Mining [article]

Jiefeng Chen, Yixuan Li, Xi Wu, Yingyu Liang, Somesh Jha
<span title="2021-06-30">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we provide a theoretically motivated method, Adversarial Training with informative Outlier Mining (ATOM), which improves the robustness of OOD detection.  ...  We show that, by mining informative auxiliary OOD data, one can significantly improve OOD detection performance, and somewhat surprisingly, generalize to unseen adversarial attacks.  ...  (c) shows the hardest examples mined from TinyImages w.r.t CIFAR-10. D Fig. 5 : 5 On CIFAR-10, we train the model with objective (1) for 100 epochs without informative outlier mining.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.15207v4">arXiv:2006.15207v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6ga4heb22va6nknpdbivqm5cum">fatcat:6ga4heb22va6nknpdbivqm5cum</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210625145905/https://arxiv.org/pdf/2006.15207v3.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/56/a7/56a7ec9b41c2f9ace40f306e8cef36787bf74ce6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.15207v4" 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>

Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation [article]

Guolei Sun and Wenguan Wang and Jifeng Dai and Luc Van Gool
<span title="2020-07-08">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Current popular solutions leverage object localization maps from classifiers as supervision signals, and struggle to make the localization maps capture more complete object content.  ...  , drives the classifier to identify the unshared semantics from the rest, uncommon objects.  ...  image pairs, for fully mining supervision signals from weak supervision.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.01947v2">arXiv:2007.01947v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pl3dnpopb5dkheytvisnepvtci">fatcat:pl3dnpopb5dkheytvisnepvtci</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200710110824/https://arxiv.org/pdf/2007.01947v2.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/41/5a/415a1db8bc9a92342c4b0f4ad150692e3766dab2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.01947v2" 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>

Deep image mining for diabetic retinopathy screening

Gwenolé Quellec, Katia Charrière, Yassine Boudi, Béatrice Cochener, Mathieu Lamard
<span title="">2017</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/kpkfymbkufcnzjfc5ydyokby4y" style="color: black;">Medical Image Analysis</a> </i> &nbsp;
Because it does not rely on expert knowledge or manual segmentation for detecting relevant patterns, the proposed solution is a promising image mining tool, which has the potential to discover new biomarkers  ...  In other words, a ConvNet trained for image-level classification can be used to detect lesions as well.  ...  The primary objective of this study is to find a way to detect lesions, or other biomarkers of DR, using deep learning algorithms supervised at the image level.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.media.2017.04.012">doi:10.1016/j.media.2017.04.012</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/28511066">pmid:28511066</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wnunezhvnfhxnj6t7bflgfldqm">fatcat:wnunezhvnfhxnj6t7bflgfldqm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200828082433/https://arxiv.org/pdf/1610.07086v2.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/83/a6/83a6f6c5347c74a590985de27665beb4cf66ef4c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.media.2017.04.012"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Cost-Effective Object Detection: Active Sample Mining With Switchable Selection Criteria

Keze Wang, Liang Lin, Xiaopeng Yan, Ziliang Chen, Dongyu Zhang, Lei Zhang
<span title="">2018</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/j6amxna35bbs5p42wy5crllu2i" style="color: black;">IEEE Transactions on Neural Networks and Learning Systems</a> </i> &nbsp;
In this work, by developing a principled active sample mining (ASM) framework, we demonstrate that cost-effectively mining samples from these unlabeled majority data is key to training more powerful object  ...  The proposed process can be compatible with mini-batch based training (i.e., using a batch of unlabeled or partially labeled data as a one-time input) for object detection.  ...  To harness rich information from the vast amount of visual data available, both semi-supervised and weakly supervised approaches for object detection have been proposed. Hoffman et al.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tnnls.2018.2852783">doi:10.1109/tnnls.2018.2852783</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/30059324">pmid:30059324</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cezwtcpvibekrpyzohxjzanokm">fatcat:cezwtcpvibekrpyzohxjzanokm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190219012326/http://pdfs.semanticscholar.org/13a6/0e75d05ef4e1ae688526bb5a4b1859a65501.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/a6/13a60e75d05ef4e1ae688526bb5a4b1859a65501.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tnnls.2018.2852783"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Cost-effective Object Detection: Active Sample Mining with Switchable Selection Criteria [article]

Keze Wang and Liang Lin and Xiaopeng Yan and Ziliang Chen and Dongyu Zhang and Lei Zhang
<span title="2019-01-12">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, by developing a principled active sample mining (ASM) framework, we demonstrate that cost-effectively mining samples from these unlabeled majority data is key to training more powerful object  ...  The proposed process can be compatible with mini-batch based training (i.e., using a batch of unlabeled or partially labeled data as a one-time input) for object detection.  ...  To harness rich information from the vast amount of visual data available, both semi-supervised and weakly supervised approaches for object detection have been proposed. Hoffman et al.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1807.00147v3">arXiv:1807.00147v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hp6xlxwanncx5p4jf5v2dxwnii">fatcat:hp6xlxwanncx5p4jf5v2dxwnii</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200928053712/https://arxiv.org/pdf/1807.00147v2.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/39/40/3940212416efab1b26ff5f730a3d9b35cb8f7018.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1807.00147v3" 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>

Interleaved Text/Image Deep Mining on a Large-Scale Radiology Database for Automated Image Interpretation [article]

Hoo-Chang Shin, Le Lu, Lauren Kim, Ari Seff, Jianhua Yao, Ronald M. Summers
<span title="2015-05-04">2015</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We present an interleaved text/image deep learning system to extract and mine the semantic interactions of radiology images and reports from a national research hospital's Picture Archiving and Communication  ...  With natural language processing, we mine a collection of representative ~216K two-dimensional key images selected by clinicians for diagnostic reference, and match the images with their descriptions in  ...  Acknowledgments This work was supported in part by the Intramural Research Program of the National Institutes of Health Clinical Center, and in part by a grant from the KRIBB Research Initiative Program  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1505.00670v1">arXiv:1505.00670v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pwpfinxrh5hixl6rnjezaqci3e">fatcat:pwpfinxrh5hixl6rnjezaqci3e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930125947/https://arxiv.org/pdf/1505.00670v1.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/46/4c/464c21d54339c3f6e624ce026fef53b19c1edd86.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1505.00670v1" 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 Style Mining for One-Shot Unsupervised Domain Adaptation [article]

Yawei Luo, Ping Liu, Tao Guan, Junqing Yu, Yi Yang
<span title="2020-04-13">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To this end, we propose a novel Adversarial Style Mining approach, which combines the style transfer module and task-specific module into an adversarial manner.  ...  Unlike traditional Unsupervised Domain Adaptation, it assumes that only one unlabeled target sample can be available when learning to adapt.  ...  Experimental results on both classification and segmentation tasks validate the effectiveness of ASM, which yields state-of-the-art performance compared with other domain adaptation approaches in the one-shot  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.06042v1">arXiv:2004.06042v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zonf24qryvexzh2sjmi467tbpq">fatcat:zonf24qryvexzh2sjmi467tbpq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200415013740/https://arxiv.org/pdf/2004.06042v1.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/2004.06042v1" 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>

Mining Label Distribution Drift in Unsupervised Domain Adaptation [article]

Peizhao Li, Zhengming Ding, Hongfu Liu
<span title="2020-06-16">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Unsupervised domain adaptation targets to transfer task knowledge from labeled source domain to related yet unlabeled target domain, and is catching extensive interests from academic and industrial areas  ...  Finally, different from general domain adaptation experiments, we modify domain adaptation datasets to create the considerable label distribution drift between source and target domain.  ...  ImageCLEF-DA 1 contains 600 images per domain taken from three objects recognition datasets, Caltech-256 (C), ImageNet ILSVRC 2012 (I), and Pascal VOC 2012 (P).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.09565v1">arXiv:2006.09565v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pkpzkxeiijhqfas3h23zjh5rcy">fatcat:pkpzkxeiijhqfas3h23zjh5rcy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200623144423/https://arxiv.org/pdf/2006.09565v1.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/2006.09565v1" 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>

Visual Search at eBay

Fan Yang, Ajinkya Kale, Yury Bubnov, Leon Stein, Qiaosong Wang, Hadi Kiapour, Robinson Piramuthu
<span title="">2017</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/fqqihtxlu5bvfaqxjyvqcob35a" style="color: black;">Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD &#39;17</a> </i> &nbsp;
Supervised approach for optimized search limited to top predicted categories and also for compact binary signature are key to scale up without compromising accuracy and precision.  ...  In this paper, we propose a novel end-to-end approach for scalable visual search infrastructure.  ...  We also learn binary image representations from deep CNN with full supervision instead of using low-level visual features [19] or expensive oating point deep features [10] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3097983.3098162">doi:10.1145/3097983.3098162</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/kdd/YangKBSWKP17.html">dblp:conf/kdd/YangKBSWKP17</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/s6v4wd3r7fgp5eiywcohonhjsa">fatcat:s6v4wd3r7fgp5eiywcohonhjsa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201009162935/https://arxiv.org/pdf/1706.03154v1.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/4f/1e/4f1e0e8f79d02526159bbe2ec725aabc51e15495.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3097983.3098162"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 1,572 results