Filters








64,807 Hits in 4.7 sec

Multi-Label Adversarial Perturbations [article]

Qingquan Song, Haifeng Jin, Xiao Huang, Xia Hu
2019 arXiv   pre-print
Several interesting findings including an unpolished defensive strategy, which could potentially enhance the interpretability and robustness of multi-label deep learning models, are further presented and  ...  Experiments on real-world multi-label image classification and ranking problems demonstrate the effectiveness of our proposed frameworks and provide insights of the vulnerability of multi-label deep learning  ...  deep learning models.  ... 
arXiv:1901.00546v1 fatcat:fiwbeyifb5g2pje7rc2dnppmk4

Towards multi-label classification: Next step of machine learning for microbiome research

Shunyao Wu, Yuzhu Chen, Zhiruo Li, Jian Li, Fengyang Zhao, Xiaoquan Su
2021 Computational and Structural Biotechnology Journal  
multi-label classification in microbiome-based studies.  ...  Then we prospect a further step of ML towards multi-label classification that potentially solves the aforementioned problem, including a series of promising strategies and key technical issues for applying  ...  Deep learning performs feature extraction automatically and trains deep neural networks in an end-to-end way [58] , which can alleviate the high dimensionality introduced by the complexity of microbial  ... 
doi:10.1016/j.csbj.2021.04.054 pmid:34093989 pmcid:PMC8131981 fatcat:7z5esebtpjgudospdbbmmpicvu

Using Deep Learning and Machine Learning to Detect Epileptic Seizure with Electroencephalography (EEG) Data [article]

Haotian Liu, Lin Xi, Ying Zhao, Zhixiang Li
2019 arXiv   pre-print
The prediction of epileptic seizure has always been extremely challenging in medical domain.  ...  sufficient medical data provided for researchers to do training of machine learning models.  ...  If the deep learning architecture is better designed, a better performance in multi-label classification is expected.  ... 
arXiv:1910.02544v1 fatcat:3go76afkvzatxfrafmy43wdn3m

Pose Guided Attention for Multi-label Fashion Image Classification [article]

Beatriz Quintino Ferreira, João P. Costeira, Ricardo G. Sousa, Liang-Yan Gui, João P. Gomes
2019 arXiv   pre-print
We propose a compact framework with guided attention for multi-label classification in the fashion domain.  ...  Additionally, we show that our semantic attention module brings robustness to large quantities of wrong annotations and provides more interpretable results.  ...  In this work we propose a CNN model that jointly learns to predict fashion categories (multi-class problem) and attributes (multi-label problem) by focusing on the relevant image regions through a guided  ... 
arXiv:1911.05024v1 fatcat:cucamml42vg6vpbe3zj4t7nguu

Using Deep Learning and Machine Learning to Detect Epileptic Seizure with Electroencephalography (EEG) Data

Haotian Liu, Lin Xi, Ying Zhao, Zhixiang Li
2019 Machine Learning Research  
and 3 deep learning architecture (including convolutional neural network (CNN), long-short term network (LSTM) and Gated Recurrent Unit (GRU)) to conduct binary and multi-label brain activities classification  ...  In conclusion, machine learning and deep learning demonstrated their potential usage in epileptic seizure identification using EEG raw data.  ...  Table 1 . 1 The performance of 6 machine learning classifiers and 3 deep learning networks on multi-label EEG classification. Precision on each label and average accuracy were reported.  ... 
doi:10.11648/j.mlr.20190403.11 fatcat:lujodxoturfs3dwpwpauiz4wgy

Estimating Uncertainty in Deep Learning for Reporting Confidence: An Application on Cell Type Prediction in Testes Based on Proteomics

Biraja Ghoshal, Cecilia Lindskog, Allan Tucker
2020 International Symposium on Intelligent Data Analysis  
To the best of our knowledge, this is the first deep learning study which quantifies uncertainty and model interpretability in multi-label classification; as well as applying it to the problem of recognising  ...  Multi-label classification in deep learning is a practical yet challenging task, because class overlaps in the feature space means that each instance is associated with multiple class labels.  ...  Deep learning models are often accused of being "black boxes", so they need to be precise, interpretable, and uncertainty in predictions must be well understood.  ... 
doi:10.1007/978-3-030-44584-3_18 dblp:conf/ida/GhoshalLT20 fatcat:ywvh7w6k5rapvifrb7ucdja3le

Imbalanced Deep Learning by Minority Class Incremental Rectification [article]

Qi Dong, Shaogang Gong, Xiatian Zhu
2018 arXiv   pre-print
In particular, existing deep learning methods consider mostly either class balanced data or moderately imbalanced data in model training, and ignore the challenge of learning from significantly imbalanced  ...  To address this problem, we formulate a class imbalanced deep learning model based on batch-wise incremental minority (sparsely sampled) class rectification by hard sample mining in majority (frequently  ...  data with multi-label semantic interpretations.  ... 
arXiv:1804.10851v1 fatcat:or7a5exm5faibfch2uahhcxca4

Imbalanced Deep Learning by Minority Class Incremental Rectification

Qi Dong, Shaogang Gong, Xiatian Zhu
2018 IEEE Transactions on Pattern Analysis and Machine Intelligence  
In particular, existing deep learning methods consider mostly either class balanced data or moderately imbalanced data in model training, and ignore the challenge of learning from significantly imbalanced  ...  To address this problem, we formulate a class imbalanced deep learning model based on batch-wise incremental minority (sparsely sampled) class rectification by hard sample mining in majority (frequently  ...  data with multi-label semantic interpretations.  ... 
doi:10.1109/tpami.2018.2832629 pmid:29993438 fatcat:iw6vssebr5eixdzw2qyurcveyi

Aerial Scene Parsing: From Tile-level Scene Classification to Pixel-wise Semantic Labeling [article]

Yang Long and Gui-Song Xia and Liangpei Zhang and Gong Cheng and Deren Li
2022 arXiv   pre-print
Moreover, our designed hierarchical multi-task learning method achieves the state-of-the-art pixel-wise classification on the challenging GID, bridging the tile-level scene classification toward pixel-wise  ...  semantic labeling for aerial image interpretation.  ...  classification toward pixel-wise semantic parsing for aerial image interpretation.  ... 
arXiv:2201.01953v2 fatcat:ikigc6f44rfw3eiirijjgdd2pu

Deep Learning with Attention to Predict Gestational Age of the Fetal Brain [article]

Liyue Shen, Katie Shpanskaya, Edward Lee, Emily McKenna, Maryam Maleki, Quin Lu, Safwan Halabi, John Pauly, Kristen Yeom
2018 arXiv   pre-print
This study develops an attention-based deep learning model to predict gestational age of the fetal brain.  ...  Our extensive experiments show age prediction performance with R2 = 0.94 using multi-view MRI and attention.  ...  towards image object detection and interpretation [2] .  ... 
arXiv:1812.07102v1 fatcat:wtub24zp35d3jdgaifm47t2uhy

Fairness in Deep Learning: A Computational Perspective [article]

Mengnan Du, Fan Yang, Na Zou, Xia Hu
2020 arXiv   pre-print
reliable deep learning systems.  ...  Therefore, fairness in deep learning has attracted tremendous attention recently.  ...  Second, it remains a challenge to diagnose and address the deep learning fairness problem. Deep opaque and hard to comprehend.  ... 
arXiv:1908.08843v2 fatcat:kaaevm64fbctpjfdycv5uz3dhi

Deep Learning applications for COVID-19

Connor Shorten, Taghi M. Khoshgoftaar, Borko Furht
2021 Journal of Big Data  
These limitations include Interpretability, Generalization Metrics, Learning from Limited Labeled Data, and Data Privacy.  ...  We begin by evaluating the current state of Deep Learning and conclude with key limitations of Deep Learning for COVID-19 applications.  ...  Acknowledgements We would like to thank the reviewers in the Data Mining and Machine Learning Laboratory at Florida Atlantic University.  ... 
doi:10.1186/s40537-020-00392-9 pmid:33457181 pmcid:PMC7797891 fatcat:aokxo63z2rhdpfxo3egyf3xpcm

Multi-label Image Recognition by Recurrently Discovering Attentional Regions [article]

Zhouxia Wang, Tianshui Chen, Guanbin Li, Ruijia Xu, Liang Lin
2017 arXiv   pre-print
This paper proposes a novel deep architecture to address multi-label image recognition, a fundamental and practical task towards general visual understanding.  ...  In this work, we achieve the interpretable and contextualized multi-label image classification by developing a recurrent memorized-attention module.  ...  In this way, our approach enables to learn a contextualized and interpretable region-label relevance while improving the discriminability for multi-label classification.  ... 
arXiv:1711.02816v1 fatcat:3tnuizsbqng4dp46cteuqinxpu

Damage detection using in-domain and cross-domain transfer learning [article]

Zaharah A. Bukhsh, Nils Jansen, Aaqib Saeed
2021 arXiv   pre-print
The pre-trained models are also evaluated for their ability to cope with the extremely low-data regime.  ...  Likewise, we also provide visual explanations of predictive models to enable algorithmic transparency and provide insights to experts about the intrinsic decision-logic of typically black-box deep models  ...  Mundt et al., [32] treated the damage classification problem in multi-label multi-target settings in which the exact match of predicted and actual multi-labels is ensured.  ... 
arXiv:2102.03858v1 fatcat:y5u3u2ylivb53fzd5ms35riczq

How to Train Your Deep Neural Network with Dictionary Learning [article]

Vanika Singhal, Shikha Singh, Angshul Majumdar
2016 arXiv   pre-print
In the final layer one needs to use the label consistent dictionary learning formulation for classification.  ...  We compare our proposed framework with existing state-of-the-art deep learning techniques on benchmark problems; we are always within the top 10 results.  ...  We show that our technique always ranks among the top few on benchmark deep learning datasets.  ... 
arXiv:1612.07454v1 fatcat:l5nsnnlbj5bt7mc7owu54pla6y
« Previous Showing results 1 — 15 out of 64,807 results