Filters








24 Hits in 5.5 sec

Adversarial Mixing Policy for Relaxing Locally Linear Constraints in Mixup

Guang Liu, Yuzhao Mao, Huang Hailong, Gao Weiguo, Li Xuan
<span title="">2021</span> <i title="Association for Computational Linguistics"> Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing </i> &nbsp; <span class="release-stage">unpublished</span>
To address these issues, we propose the Adversarial Mixing Policy (AMP), organized in a "min-max-rand" formulation, to relax the Locally Linear Constraints in Mixup.  ...  Mixup is a recent regularizer for current deep classification networks.  ...  Acknowledgments We thank Prof.Xiaojie Wang and Prof.Fangxiang Feng from BUPT for their valuable feedback on an earlier draft of this paper, and Yang Du from XDF for her suggestions of English writing for  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/2021.emnlp-main.238">doi:10.18653/v1/2021.emnlp-main.238</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rw4irk6fczcefeb42wztpjx5yu">fatcat:rw4irk6fczcefeb42wztpjx5yu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211105033944/https://aclanthology.org/2021.emnlp-main.238.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/af/a8/afa8b13dee7d7ad1be5cfe12c50331873f227649.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/2021.emnlp-main.238"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

MixUp as Locally Linear Out-Of-Manifold Regularization [article]

Hongyu Guo and Yongyi Mao and Richong Zhang
<span title="2018-11-22">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we develop an understanding for MixUp as a form of "out-of-manifold regularization", which imposes certain "local linearity" constraints on the model's input space beyond the data manifold  ...  In a nutshell, manifold intrusion in MixUp is a form of under-fitting resulting from conflicts between the synthetic labels of the mixed-up examples and the labels of original training data.  ...  Identifying the constraints imposed by MixUp with a set of "locally linear" constraints, we call such a data-dependent regularization scheme a "locally linear out-of-manifold" regularization scheme.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1809.02499v3">arXiv:1809.02499v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bdipgqbhtzfs7kqbetdcly4pn4">fatcat:bdipgqbhtzfs7kqbetdcly4pn4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200824072701/https://arxiv.org/pdf/1809.02499v3.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/c8/4f/c84f43a8066253905da479b128dba1da633e5df9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1809.02499v3" 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>

MixUp as Locally Linear Out-of-Manifold Regularization

Hongyu Guo, Yongyi Mao, Richong Zhang
<span title="2019-07-17">2019</span> <i title="Association for the Advancement of Artificial Intelligence (AAAI)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wtjcymhabjantmdtuptkk62mlq" style="color: black;">PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE</a> </i> &nbsp;
In this paper, we develop an understanding for MixUp as a form of "out-of-manifold regularization", which imposes certain "local linearity" constraints on the model's input space beyond the data manifold  ...  In a nutshell, manifold intrusion in MixUp is a form of under-fitting resulting from conflicts between the synthetic labels of the mixed-up examples and the labels of original training data.  ...  , by the National Natural Science Foundation of China (61772059), and by the Beijing Advanced Innovation Center for Big Data and Brain Computing.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v33i01.33013714">doi:10.1609/aaai.v33i01.33013714</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/s4twlhmgvfhlfovzsqzvepctri">fatcat:s4twlhmgvfhlfovzsqzvepctri</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200929053436/https://aaai.org/ojs/index.php/AAAI/article/download/4256/4134" 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/1e/4c/1e4cbcef1164dbf3f12e8115e14b84e995f0e418.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v33i01.33013714"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

An overview of mixing augmentation methods and augmentation strategies [article]

Dominik Lewy, Jacek Mańdziuk
<span title="2022-04-18">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This survey focuses on two DA research streams: image mixing and automated selection of augmentation strategies.  ...  This review mainly covers the methods published in the materials of top-tier conferences and in leading journals in the years 2017-2021.  ...  -Categorization of adversarial images -Mixup [82] , Manifold Mixup [73] , Cut-Mix [80] , Puzzle Mix [36] . -Weakly supervised object localization -CutMix [80] , RICAP [68] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.09887v2">arXiv:2107.09887v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/isue7dmwxzdihgwiq2efj3k3qm">fatcat:isue7dmwxzdihgwiq2efj3k3qm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220519051835/https://arxiv.org/pdf/2107.09887v2.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/ae/92/ae92ee99f3a791bb5a5cdc0147311e1cd8f13694.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.09887v2" 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>

Interpolation Consistency Training for Semi-supervised Learning

Vikas Verma, Alex Lamb, Juho Kannala, Yoshua Bengio, David Lopez-Paz
<span title="">2019</span> <i title="International Joint Conferences on Artificial Intelligence Organization"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vfwwmrihanevtjbbkti2kc3nke" style="color: black;">Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence</a> </i> &nbsp;
We introduce Interpolation Consistency Training (ICT), a simple and computation efficient algorithm for training Deep Neural Networks in the semi-supervised learning paradigm.  ...  In classification problems, ICT moves the decision boundary to low-density regions of the data distribution.  ...  There exist many future directions to be explored along the mixing based methods. For example, in Manifold Mixup, we randomly selected the mixing coefficient λ and the layer for mixing.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2019/504">doi:10.24963/ijcai.2019/504</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ijcai/VermaLKBL19.html">dblp:conf/ijcai/VermaLKBL19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bucjagfaybei5boup7b56yqngu">fatcat:bucjagfaybei5boup7b56yqngu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210428044432/https://aaltodoc.aalto.fi/bitstream/handle/123456789/59150/isbn9789526401607.pdf;jsessionid=85B6AB4BD6BD30138F1E3BAC4B7A3429?sequence=1" 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/fb/a7/fba78941b2f83b497d1f4ac9e2a405456c6bd8dc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2019/504"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Noisy Feature Mixup [article]

Soon Hoe Lim, N. Benjamin Erichson, Francisco Utrera, Winnie Xu, Michael W. Mahoney
<span title="2021-11-21">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We introduce Noisy Feature Mixup (NFM), an inexpensive yet effective method for data augmentation that combines the best of interpolation based training and noise injection schemes.  ...  Rather than training with convex combinations of pairs of examples and their labels, we use noise-perturbed convex combinations of pairs of data points in both input and feature space.  ...  Our conclusions do not necessarily reflect the position or the policy of our sponsors, and no official endorsement should be inferred. We are also grateful for the generous support from Amazon AWS.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.02180v2">arXiv:2110.02180v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xkhk3lbg2vcapfhisdbiijxaua">fatcat:xkhk3lbg2vcapfhisdbiijxaua</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211130174331/https://arxiv.org/pdf/2110.02180v2.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/cb/4c/cb4c989386da6c2381c358bf6f37740785b20e4d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.02180v2" 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 on Deep Semi-supervised Learning [article]

Xiangli Yang, Zixing Song, Irwin King, Zenglin Xu
<span title="2021-08-23">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In addition to the progress in the past few years, we further discuss some shortcomings of existing methods and provide some tentative heuristic solutions for solving these open problems.  ...  We first present a taxonomy for deep semi-supervised learning that categorizes existing methods, including deep generative methods, consistency regularization methods, graph-based methods, pseudo-labeling  ...  Therefore, Mixup extends the training data set by a hard constraint that linear interpolations of samples should lead to the linear interpolations of the corresponding labels. ICT.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.00550v2">arXiv:2103.00550v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lymncf5wavgkhaenbvqlyvhuaa">fatcat:lymncf5wavgkhaenbvqlyvhuaa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210830050427/https://arxiv.org/pdf/2103.00550v2.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/e4/15/e415d9e2e5765d878ddaf8dd576ba54d5906517e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.00550v2" 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>

Enhancing MR Image Segmentation with Realistic Adversarial Data Augmentation [article]

Chen Chen, Chen Qin, Cheng Ouyang, Zeju Li, Shuo Wang, Huaqi Qiu, Liang Chen, Giacomo Tarroni, Wenjia Bai, Daniel Rueckert
<span title="2022-04-23">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The proposed adversarial data augmentation does not rely on generative networks and can be used as a plug-in module in general segmentation networks.  ...  To address this challenge, we propose AdvChain, a generic adversarial data augmentation framework, aiming at improving both the diversity and effectiveness of training data for medical image segmentation  ...  Compared to data-mixing based methods such as Mixmatch (Berthelot et al., 2019), which generates unrealis- tic mixed images with linear interpolation to ensure the 'linear- ity' of the network, the proposed  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.03429v2">arXiv:2108.03429v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/m24wykdkbna3fdtq2t5qdlgq2i">fatcat:m24wykdkbna3fdtq2t5qdlgq2i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220427235813/https://arxiv.org/pdf/2108.03429v2.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/cb/54/cb54189222bedae46e9f07b8585dcfea1065da77.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.03429v2" 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>

Advances in adversarial attacks and defenses in computer vision: A survey [article]

Naveed Akhtar, Ajmal Mian, Navid Kardan, Mubarak Shah
<span title="2021-09-02">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In [2], we reviewed the contributions made by the computer vision community in adversarial attacks on deep learning (and their defenses) until the advent of year 2018.  ...  Besides a comprehensive literature review, the article also provides concise definitions of technical terminologies for non-experts in this domain.  ...  For example, in [351] , a mixup training of neural networks was introduced.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.00401v2">arXiv:2108.00401v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/23gw74oj6bblnpbpeacpg3hq5y">fatcat:23gw74oj6bblnpbpeacpg3hq5y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210906192640/https://arxiv.org/pdf/2108.00401v2.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/1a/08/1a0829a7bef8ea3ecb33b55871b4498dd328ff68.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.00401v2" 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>

Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning [article]

Lionel Blondé, Pablo Strasser, Alexandros Kalousis
<span title="2022-01-19">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We consider the case of off-policy generative adversarial imitation learning, and perform an in-depth review, qualitative and quantitative, of the method.  ...  We show that forcing the learned reward function to be local Lipschitz-continuous is a sine qua non condition for the method to perform well.  ...  As for the activations functions used in the neural networks, we used ReLU non-linearities in both the actor and critic, and used Leaky-ReLU [82] non-linearities with a leak of 0.1 in the discriminator  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.16785v3">arXiv:2006.16785v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vtb6fvqrqbf35hnbyzob3utz2u">fatcat:vtb6fvqrqbf35hnbyzob3utz2u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220121021223/https://arxiv.org/pdf/2006.16785v3.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/33/35/3335f941b9e0b4be6eb38096501051467b16f795.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.16785v3" 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>

DABS: A Domain-Agnostic Benchmark for Self-Supervised Learning [article]

Alex Tamkin, Vincent Liu, Rongfei Lu, Daniel Fein, Colin Schultz, Noah Goodman
<span title="2021-11-23">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Each domain contains an unlabeled dataset for pretraining; the model is then is scored based on its downstream performance on a set of labeled tasks in the domain.  ...  solution for arbitrary domains.  ...  Acknowledgments and Funding Disclosures We would like to thank Shyamal Buch, Jesse Mu, Jared Davis, Daniel Rothchild, and Mike Wu for useful discussions and feedback.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.12062v1">arXiv:2111.12062v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/trus5nvoirgj7pfhvqd56pgpea">fatcat:trus5nvoirgj7pfhvqd56pgpea</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211125193950/https://arxiv.org/pdf/2111.12062v1.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/cb/07/cb07d1b211aef6ab178d812c3617cb9d1753af1f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.12062v1" 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>

Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications [article]

Khaled B. Letaief, Yuanming Shi, Jianmin Lu, Jianhua Lu
<span title="2021-11-24">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we shall provide our vision for scalable and trustworthy edge AI systems with integrated design of wireless communication strategies and decentralized machine learning models.  ...  deep learning and big data analytics based AI systems require tremendous computation and communication resources, causing significant latency, energy consumption, network congestion, and privacy leakage in  ...  and accuracy constraints for wireless FL.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.12444v1">arXiv:2111.12444v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/crrbtfylvjeihogumggdnxcbpq">fatcat:crrbtfylvjeihogumggdnxcbpq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211129151828/https://arxiv.org/pdf/2111.12444v1.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/b3/c6/b3c62bcfa3fe86ecd4d1706e70f4b422c78674a4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.12444v1" 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>

Knowledge Augmented Machine Learning with Applications in Autonomous Driving: A Survey [article]

Julian Wörmann, Daniel Bogdoll, Etienne Bührle, Han Chen, Evaristus Fuh Chuo, Kostadin Cvejoski, Ludger van Elst, Tobias Gleißner, Philip Gottschall, Stefan Griesche, Christian Hellert, Christian Hesels (+34 others)
<span title="2022-05-10">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The reasons for this are manifold and range from time and cost constraints to ethical considerations.  ...  However, the subsequent application of these models often involves scenarios that are inadequately represented in the data used for training.  ...  The authors in [763] propose virtual adversarial training for anatomicallyplausible image segmentation, i.e., they generate adversarial samples that violate the topological constraints and let the network  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.04712v1">arXiv:2205.04712v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/u2bgxr2ctnfdjcdbruzrtjwot4">fatcat:u2bgxr2ctnfdjcdbruzrtjwot4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220514025008/https://arxiv.org/pdf/2205.04712v1.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/f8/53/f8530faaea20a4aa18229fcc13c076600da8d5b2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.04712v1" 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 Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges [article]

Moloud Abdar, Farhad Pourpanah, Sadiq Hussain, Dana Rezazadegan, Li Liu, Mohammad Ghavamzadeh, Paul Fieguth, Xiaochun Cao, Abbas Khosravi, U Rajendra Acharya, Vladimir Makarenkov, Saeid Nahavandi
<span title="2021-01-06">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This study reviews recent advances in UQ methods used in deep learning. Moreover, we also investigate the application of these methods in reinforcement learning (RL).  ...  In this regard, researchers have proposed different UQ methods and examined their performance in a variety of applications such as computer vision (e.g., self-driving cars and object detection), image  ...  For example, Sinha et al. [565] proposed a new Al in an adversarial manner which is called VAAL (Variational Adversarial AL).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.06225v4">arXiv:2011.06225v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wwnl7duqwbcqbavat225jkns5u">fatcat:wwnl7duqwbcqbavat225jkns5u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210113234503/https://arxiv.org/pdf/2011.06225v4.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/f1/4f/f14fc9e399d44463a17cc47a9b339b58f6ef7502.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.06225v4" 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 from Noisy Labels with Deep Neural Networks: A Survey [article]

Hwanjun Song, Minseok Kim, Dongmin Park, Yooju Shin, Jae-Gil Lee
<span title="2022-03-10">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Finally, we present several promising research directions that can serve as a guideline for future studies. All the contents will be available at https://github.com/songhwanjun/Awesome-Noisy-Labels.  ...  Deep learning has achieved remarkable success in numerous domains with help from large amounts of big data.  ...  In contrast, mixup [95] x mix = λx i + (1 − λ)x j and y mix = λỹ i + (1 − λ)ỹ j , (6) where λ ∈ [0, 1] is the balance parameter between two examples.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.08199v7">arXiv:2007.08199v7</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/c5ztk4jfpfddrhqvf6phcy32de">fatcat:c5ztk4jfpfddrhqvf6phcy32de</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220312220221/https://arxiv.org/pdf/2007.08199v7.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/5f/fe/5ffe9b1d8219438f0343995ad3ea1a888e3d9f8e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.08199v7" 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 24 results