Filters








119,621 Hits in 2.9 sec

Deep Elastic Networks with Model Selection for Multi-Task Learning [article]

Chanho Ahn, Eunwoo Kim, Songhwai Oh
<span title="2019-09-11">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To this end, we propose an efficient approach to exploit a compact but accurate model in a backbone architecture for each instance of all tasks.  ...  In this work, we consider the problem of instance-wise dynamic network model selection for multi-task learning.  ...  In this work, we aim to develop an instance-aware dynamic model selection approach for a single network to learn multiple tasks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.04860v1">arXiv:1909.04860v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ifhkfaboevdwfajvjid4abg2wy">fatcat:ifhkfaboevdwfajvjid4abg2wy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200825162828/https://arxiv.org/pdf/1909.04860v1.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/ce/96/ce96bf213774826d825f12dec4f4328bc9006ce5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.04860v1" 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 new SAT-based ATPG for generating highly compacted test sets

Stephan Eggersglu, Rene Krenz-Baath, Andreas Glowatz, Friedrich Hapke, Rolf Drechsler
<span title="">2012</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/6zmpupdvf5fhhnjefe33o3wvm4" style="color: black;">2012 IEEE 15th International Symposium on Design and Diagnostics of Electronic Circuits &amp; Systems (DDECS)</a> </i> &nbsp;
Experimental results on large industrial circuits show that the approach is able to reduce the pattern count of up to 63% compared to state-of-the-art dynamic compaction techniques.  ...  In contrast to previous SAT-based ATPG techniques which were focused on dealing with hard single faults, the proposed approach employs the robustness of SAT-solvers to primarily push test compaction.  ...  SAT instance for Multiple Target Test Generation faults and has not to be calculated for each fault separately as typically done by structural approaches using multiple path sensitization.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/ddecs.2012.6219063">doi:10.1109/ddecs.2012.6219063</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ddecs/EggersglussKGHD12.html">dblp:conf/ddecs/EggersglussKGHD12</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4zpcdgwokfb3tgo2turwginwby">fatcat:4zpcdgwokfb3tgo2turwginwby</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190828205440/http://www.informatik.uni-bremen.de:80/agra/doc/konf/12DDECS-MultipleTarget.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/62/ce/62ce43a7d0bbc9fcabbbbd1b6520f793f5f3cf7f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/ddecs.2012.6219063"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Learning Pain from Action Unit Combinations: A Weakly Supervised Approach via Multiple Instance Learning [article]

Zhanli Chen, Rashid Ansari, Diana J. Wilkie
<span title="2018-02-20">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Two weakly supervised learning frameworks namely multiple instance learning (MIL) and multiple clustered instance learning (MCIL) are employed corresponding to each data structure to learn pain from video  ...  Multiple Clustered Instance Learning (MCIL) proposed by Xu et al.  ...  Multiple Clustered Instance Learning In the compact structure feature settings, scores of all AU combinations are encoded in one feature vector, which can be conveniently handled by the original MIL framework  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1712.01496v2">arXiv:1712.01496v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dp6r3kng5zhxdce5tfxihumw5a">fatcat:dp6r3kng5zhxdce5tfxihumw5a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200915151540/https://arxiv.org/pdf/1712.01496v2.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/cc/8f/cc8ff69db9e90579c83b41e94a887023c1850608.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1712.01496v2" 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>

Self-supervised Speaker Recognition Training Using Human-Machine Dialogues [article]

Metehan Cekic, Ruirui Li, Zeya Chen, Yuguang Yang, Andreas Stolcke, Upamanyu Madhow
<span title="2022-02-17">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
However, the supervisory information in such dialogues is inherently noisy, as multiple speakers may speak to a device in the course of the same dialogue.  ...  Learning speaker representations, in the context of supervised learning, heavily depends on both clean and sufficient labeled data, which is always difficult to acquire.  ...  In this way, the model will suffer less from centroids aggregating multiple speakers while learning from all utterances in a dialogue.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.03484v2">arXiv:2202.03484v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zlqf4jekbnb3tgnjglkv6cibiq">fatcat:zlqf4jekbnb3tgnjglkv6cibiq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220530154949/https://arxiv.org/pdf/2202.03484v2.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/4d/3c/4d3c3dbef096b1e99a1438642a3655866f3b1c8d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.03484v2" 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>

Optimality-Based Analysis of XCSF Compaction in Discrete Reinforcement Learning [chapter]

Jordan T. Bishop, Marcus Gallagher
<span title="">2020</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
Learning classifier systems (LCSs) are population-based predictive systems that were originally envisioned as agents to act in reinforcement learning (RL) environments.  ...  We then introduce a novel compaction algorithm (Greedy Niche Mass Compaction - GNMC) and study its operation on XCSF's trained populations.  ...  Finally we linked our policy accuracy metric to the steps-to-goal metric used in previous work across multiple groups of compacted XCSF instances.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-58115-2_33">doi:10.1007/978-3-030-58115-2_33</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4rfouxsycfdsrjo64gnfo6puum">fatcat:4rfouxsycfdsrjo64gnfo6puum</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200915124744/https://arxiv.org/pdf/2009.01476v1.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> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-58115-2_33"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification [article]

Hao Chen, Benoit Lagadec, Francois Bremond
<span title="2021-08-18">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The main idea of instance contrastive learning is to match a same instance in different augmented views.  ...  Recently, self-supervised contrastive learning has gained increasing attention for its effectiveness in unsupervised representation learning.  ...  Self-paced Contrastive Learning (SpCL) [13] alleviates this problem by matching an instance with the centroid of the multiple positives, where each positive converges to its centroid at a uniform pace  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.16364v2">arXiv:2103.16364v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6zgw64q6s5gk5fpqbicbbaa47q">fatcat:6zgw64q6s5gk5fpqbicbbaa47q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210829113622/https://arxiv.org/pdf/2103.16364v2.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/34/6b/346bcb73a4d44f70e9f77620af51927418db9745.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.16364v2" 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>

Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID [article]

Yixiao Ge, Feng Zhu, Dapeng Chen, Rui Zhao, Hongsheng Li
<span title="2020-10-13">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The hybrid memory dynamically generates source-domain class-level, target-domain cluster-level and un-clustered instance-level supervisory signals for learning feature representations.  ...  Different from the conventional contrastive learning strategy, the proposed framework jointly distinguishes source-domain classes, and target-domain clusters and un-clustered instances.  ...  ., a reliable cluster should be consistent in clusters at multiple levels. R indep and R comp are therefore proposed to measure the independence and compactness of clusters, respectively.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.02713v2">arXiv:2006.02713v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/o3p2qjowcvaudce2twtxpok7fe">fatcat:o3p2qjowcvaudce2twtxpok7fe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201018024719/https://arxiv.org/pdf/2006.02713v2.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/2006.02713v2" 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>

Learning Complex Rare Categories with Dual Heterogeneity [chapter]

Pei Yang, Jingrui He, Jia-Yu Pan
<span title="2015-06-30">2015</span> <i title="Society for Industrial and Applied Mathematics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/viwc2ys5x5a47ogpdlftfzj5fm" style="color: black;">Proceedings of the 2015 SIAM International Conference on Data Mining</a> </i> &nbsp;
originates from multiple information sources.  ...  Existing methods for learning rare categories mainly focus on the homogeneous settings, i.e., a single task and a single view.  ...  Multi-task learning assumes that multiple tasks can benefit from certain common structures.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1137/1.9781611974010.59">doi:10.1137/1.9781611974010.59</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/sdm/YangHP15.html">dblp:conf/sdm/YangHP15</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/itun63zbg5f6zhs4m442dpby3a">fatcat:itun63zbg5f6zhs4m442dpby3a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170829130533/http://faculty.engineering.asu.edu/jingruihe/wp-content/uploads/2015/06/sdm15_m2lid.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/d1/47/d1474776a4fbb81043bc09299dc63a86884691c5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1137/1.9781611974010.59"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

CaRENets: Compact and Resource-Efficient CNN for Homomorphic Inference on Encrypted Medical Images [article]

Jin Chao, Ahmad Al Badawi, Balagopal Unnikrishnan, Jie Lin, Chan Fook Mun, James M. Brown, J. Peter Campbell, Michael Chiang, Jayashree Kalpathy-Cramer, Vijay Ramaseshan Chandrasekhar, Pavitra Krishnaswamy, Khin Mi Mi Aung
<span title="2019-01-29">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
At the core, CaRENets comprises a new FHE compact packing scheme that is tightly integrated with CNN functions.  ...  As our approach enables memory-efficient low-latency HE inference without imposing additional communication burden, it has implications for practical and secure deep learning inference in clinical imaging  ...  Acknowledgments This project was supported by funding from the Deep Learning 2.0 program at the Institute for Infocomm Research (I 2 R), A*STAR, Singapore; research grants from the US National Institutes  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1901.10074v1">arXiv:1901.10074v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wt2yjtmydzcc5kl6tsghdkx224">fatcat:wt2yjtmydzcc5kl6tsghdkx224</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191018091529/https://arxiv.org/pdf/1901.10074v1.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/d7/b2/d7b26f72d4f48d03f58f0306c4f785f9f089a888.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1901.10074v1" 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>

Learning compact parameterized skills with a single regression

Freek Stulp, Gennaro Raiola, Antoine Hoarau, Serena Ivaldi, Olivier Sigaud
<span title="">2013</span> <i title="IEEE"> 2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids) </i> &nbsp;
A common approach for achieving generality is to learn parameterizable skills from multiple demonstrations for different situations.  ...  This leads to a more general, flexible, and compact representation of parameterizable skills, as demonstrated by our empirical evaluation on the iCub and Meka humanoid robots.  ...  K task instances.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/humanoids.2013.7030008">doi:10.1109/humanoids.2013.7030008</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/osqyenn7aresnmbk7t6v45q6d4">fatcat:osqyenn7aresnmbk7t6v45q6d4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170922233833/http://www.freekstulp.net/publications/pdfs/stulp13learning.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/13/07/1307fdfb6e866fd006dc8cb3ce200e1391e671e0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/humanoids.2013.7030008"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

An Empirical Study of Building Compact Ensembles [chapter]

Huan Liu, Amit Mandvikar, Jigar Mody
<span title="">2004</span> <i title="Springer Berlin Heidelberg"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
The idea of compact ensembles is motivated to use them for effective active learning in tasks of classification of unlabeled data.  ...  We propose a heuristic method that can effectively select member classifiers to form a compact ensemble.  ...  Each bootstrap replicate contains, on the average, 63.2% of the original data, with several instances appearing multiple times.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-540-27772-9_63">doi:10.1007/978-3-540-27772-9_63</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/p7wiae2h2nh45en6v7jmtjlgaq">fatcat:p7wiae2h2nh45en6v7jmtjlgaq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20040809042101/http://www.public.asu.edu:80/~huanliu/papers/waim04.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/07/45/07451e979083a08c3a900036d26c5ff9819c2472.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-540-27772-9_63"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Tattoo Image Search at Scale: Joint Detection and Compact Representation Learning

Hu Han, Jie Li, Anil K. Jain, shiguang shan, Xilin Chen
<span title="2019-01-09">2019</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/3px634ph3vhrtmtuip6xznraqi" style="color: black;">IEEE Transactions on Pattern Analysis and Machine Intelligence</a> </i> &nbsp;
We resolve the small batch size issue inside the joint tattoo detection and compact representation learning network via random image stitch and preceding feature buffering.  ...  learning.  ...  Compact Representation Learning Compact representation learning is of particular interest because of the need for efficient methods in large-scale visual search and instance retrieval applications [28  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tpami.2019.2891584">doi:10.1109/tpami.2019.2891584</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/30629491">pmid:30629491</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zgkocarum5dmfieo4c2si44xli">fatcat:zgkocarum5dmfieo4c2si44xli</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190220101915/http://pdfs.semanticscholar.org/26c8/9f890da91119ffa16d5a23fba963257ef3fc.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/26/c8/26c89f890da91119ffa16d5a23fba963257ef3fc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tpami.2019.2891584"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Semantic Domain Adversarial Networks for Unsupervised Domain Adaptation [article]

Dapeng Hu, Jian Liang, Qibin Hou, Hanshu Yan, Yunpeng Chen, Shuicheng Yan, Jiashi Feng
<span title="2021-02-09">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we attempt to address this dilemma by devising simple and compact conditional domain adversarial training methods.  ...  ., using multiple class-wise discriminators and introducing conditional information in input or output of the domain discriminator.  ...  compactness objective.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.13274v3">arXiv:2003.13274v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yuwcf73ksbc3tfkv4dmnmaqk44">fatcat:yuwcf73ksbc3tfkv4dmnmaqk44</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200415013314/https://arxiv.org/pdf/2003.13274v2.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> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.13274v3" 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 low bit rate mobile visual search with multiple-channel coding

Rongrong Ji, Ling-Yu Duan, Jie Chen, Hongxun Yao, Yong Rui, Shih-Fu Chang, Wen Gao
<span title="">2011</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/lahlxihmo5fhzpexw7rundu24u" style="color: black;">Proceedings of the 19th ACM international conference on Multimedia - MM &#39;11</a> </i> &nbsp;
RFID tags for mobile product search), together with the visual statistics at the reference database, to learn multiple coding channels.  ...  In this paper, we propose a multiple-channel coding scheme to extract compact visual descriptors for low bit rate mobile visual search.  ...  We propose a Multiple-channel Coding based compact Visual Descriptor (MCVD) to achieve the above goal.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2072298.2072372">doi:10.1145/2072298.2072372</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/mm/JiDCYRCG11.html">dblp:conf/mm/JiDCYRCG11</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ir7dmmnitvg2fgdsitm376oqde">fatcat:ir7dmmnitvg2fgdsitm376oqde</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20120130185227/http://www.ee.columbia.edu/ln/dvmm/publications/11/low_long.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/62/ae/62ae6f7d1a12199715b9409c00577336724c216b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2072298.2072372"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Pareto Inspired Multi-objective Rule Fitness for Noise-Adaptive Rule-Based Machine Learning [chapter]

Ryan J. Urbanowicz, Randal S. Olson, Jason H. Moore
<span title="">2016</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
While evaluation over multiple performance metrics yielded mixed results, this work represents an important first step towards efficiently learning complex problem spaces without the advantage of prior  ...  We propose a Pareto-inspired multi-objective rule fitness (PIMORF) for LCS, and combine it with a complimentary rule-compaction approach (SRC).  ...  Over multiple generations, the goal is to evolve the front closer to the theoretical optimum.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-45823-6_48">doi:10.1007/978-3-319-45823-6_48</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4tiriqzeqfcxvcv7eiiawispvi">fatcat:4tiriqzeqfcxvcv7eiiawispvi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190222232919/http://pdfs.semanticscholar.org/3e56/52ce200bb9f8e2f386c52b3206bc3a09e3a8.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/3e/56/3e5652ce200bb9f8e2f386c52b3206bc3a09e3a8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-45823-6_48"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 119,621 results