Filters








3,194 Hits in 9.5 sec

Cross-Domain Review Helpfulness Prediction Based on Convolutional Neural Networks with Auxiliary Domain Discriminators

Cen Chen, Yinfei Yang, Jun Zhou, Xiaolong Li, Forrest Sheng Bao
2018 Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)  
Therefore, we propose a convolutional neural network (CNN) based model which leverages both word-level and character-based representations.  ...  To transfer knowledge between domains, we further extend our model to jointly model different domains with auxiliary domain discriminators.  ...  Conclusion In this work, we proposed a convolutional neural network (CNN) based approach that combines both word-and character-level representations, for review helpfulness prediction.  ... 
doi:10.18653/v1/n18-2095 dblp:conf/naacl/ChenYZLB18 fatcat:65ro2564mfakzndoi7jxcogo6m

Action Segmentation With Joint Self-Supervised Temporal Domain Adaptation

Min-Hung Chen, Baopu Li, Yingze Bao, Ghassan AlRegib, Zsolt Kira
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
To reduce the discrepancy, we propose Self-Supervised Temporal Domain Adaptation (SSTDA), which contains two self-supervised auxiliary tasks (binary and sequential domain prediction) to jointly align cross-domain  ...  Therefore, we exploit unlabeled videos to address this problem by reformulating the action segmentation task as a cross-domain problem with domain discrepancy caused by spatio-temporal variations.  ...  Recently, adversarial-based DA approaches [10, 11] show progress in addressing cross-domain image problems using a domain discriminator with adversarial training where domain discrimination can be regarded  ... 
doi:10.1109/cvpr42600.2020.00947 dblp:conf/cvpr/ChenLBAK20 fatcat:gz5hoxb72ndpxfpkqx73co6oke

Confidence Estimation via Auxiliary Models [article]

Charles Corbière, Nicolas Thome, Antoine Saporta, Tuan-Hung Vu, Matthieu Cord, Patrick Pérez
2021 arXiv   pre-print
We evaluate our approach on the task of failure prediction and of self-training with pseudo-labels for domain adaptation, which both necessitate effective confidence estimates.  ...  We study various network architectures and experiment with small and large datasets for image classification and semantic segmentation.  ...  Learning to predict TCP with a neural network Using TCP as confidence-rate function on a model's output would be of great help when it comes to reliably estimate its confidence.  ... 
arXiv:2012.06508v2 fatcat:i7r2xk4qyng6vdtyrnbbv4xxgq

A fault diagnosis method based on Auxiliary Classifier Generative Adversarial Network for rolling bearing

Chunming Wu, Zhou Zeng
2021 PLoS ONE  
In order to solve above problems, by combining Auxiliary Classifier Generative Adversarial Network (ACGAN) and Stacked Denoising Auto Encoder (SDAE), a novel method is proposed for fault diagnosis.  ...  Rolling bearing fault diagnosis is one of the challenging tasks and hot research topics in the condition monitoring and fault diagnosis of rotating machinery.  ...  Acknowledgments The authors would like to thank the anonymous reviewers for their critical and constructive comments, their thoughtful suggestions have helped improve this paper substantially.  ... 
doi:10.1371/journal.pone.0246905 pmid:33647055 pmcid:PMC7924884 fatcat:ewx57fafmfh67i7ie6xxnukh3m

Deep Learning meets Liveness Detection: Recent Advancements and Challenges [article]

Arian Sabaghi, Marzieh Oghbaie, Kooshan Hashemifard, Mohammad Akbari
2021 arXiv   pre-print
To shed light on this topic, a semantic taxonomy based on various features and learning methodologies is represented.  ...  In this paper, we present a comprehensive survey on the literature related to deep-feature-based FAS methods since 2017.  ...  “Deep face liveness detection based on nonlinear diffusion using convolution neural network”.  ... 
arXiv:2112.14796v1 fatcat:axar6akifnh3lgc4mbuqc5nc2i

A Survey on Adversarial Image Synthesis [article]

William Roy, Glen Kelly, Robert Leer, Frederick Ricardo
2021 arXiv   pre-print
Generative Adversarial Networks (GANs) have been extremely successful in various application domains.  ...  as possible future research directions in image synthesis with GAN.  ...  Moving from F C to convolutional neural networks (CNNs) is suitable for the image data.  ... 
arXiv:2106.16056v2 fatcat:mivx26q4x5ampfi566tipcwv3e

Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation [article]

Suman Saha, Anton Obukhov, Danda Pani Paudel, Menelaos Kanakis, Yuhua Chen, Stamatios Georgoulis, Luc Van Gool
2021 arXiv   pre-print
To capture the cross-task relationships, we propose a neural network architecture that contains task-specific and cross-task refinement heads.  ...  Motivated by this observation, we propose a novel Cross-Task Relation Layer (CTRL), which encodes task dependencies between the semantic and depth predictions.  ...  We thank Amazon Activate for EC2 credits and the anonymous reviewers for the valuable feedback and time spent.  ... 
arXiv:2105.07830v2 fatcat:xukcrguvqrddnfdyhlcrpukf34

Improving Classification Accuracy of Hand Gesture Recognition Based on 60 GHz FMCW Radar with Deep Learning Domain Adaptation

Hyo Ryun Lee, Jihun Park, Young-Joo Suh
2020 Electronics  
To verify the effectiveness of domain adaptation, a domain discriminator that cheats the classifier was applied to a deep learning network with a convolutional neural network (CNN) structure.  ...  With the recent development of small radars with high resolution, various human–computer interaction (HCI) applications using them have been developed.  ...  Representatively, the domain-adversarial neural network (DANN) [28] suggests domain adaptation by introducing a domain discriminator and gradient reversal layer to the existing neural network structure  ... 
doi:10.3390/electronics9122140 fatcat:cwxe7foifjatpnjnpzyuhxvyja

A comprehensive review on convolutional neural network in machine fault diagnosis [article]

Jinyang Jiao, Ming Zhao, Jing Lin, Kaixuan Liang
2020 arXiv   pre-print
To fill in this gap, this work attempts to review and summarize the development of the Convolutional Network based Fault Diagnosis (CNFD) approaches comprehensively.  ...  Then, the fundamental theory from the basic convolutional neural network to its variants is elaborated.  ...  Tian, Tool wear predicting based on multi-domain feature fusion by deep convolutional neural network in milling operations, J. Intell. Manuf., (2019). [190] J. Fu, J. Chu, P. Guo, Z.  ... 
arXiv:2002.07605v1 fatcat:54w3panr35bb7app4y7dfnjeqa

Learning to adapt class-specific features across domains for semantic segmentation [article]

Mikel Menta, Adriana Romero, Joost van de Weijer
2020 arXiv   pre-print
Recent advances in unsupervised domain adaptation have shown the effectiveness of adversarial training to adapt features across domains, endowing neural networks with the capability of being tested on  ...  To that aim, we design a conditional pixel-wise discriminator network, whose output is conditioned on the segmentation masks.  ...  Current DNN models to tackle pixel-prediction problems are based on Fully Convolutional Networks (FCNs) [46] .  ... 
arXiv:2001.08311v1 fatcat:xeqowbv2bzb5vaitwfuqszlj4a

Transfer Learning and Deep Domain Adaptation [chapter]

Wen Xu, Jing He, Yanfeng Shu
2020 Advances and Applications in Deep Learning [Working Title]  
Secondly, we conduct a comprehensive survey related to deep domain adaptation and categorize the recent advances into three types based on implementing approaches: fine-tuning networks, adversarial domain  ...  The intuition behind this is that deep neural networks usually have a large capacity to learn representation from one dataset and part of the information can be further used for a new task.  ...  Compared with the traditional shallow method, deep domain adaptation mainly focuses on utilizing deep neural networks to improve the performance of the predictive function F t .  ... 
doi:10.5772/intechopen.94072 fatcat:xqqzz45hybg6lgue3bowqn6hke

Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation

Suman Saha, Anton Obukhov, Danda Pani Paudel, Menelaos Kanakis, Yuhua Chen, Stamatios Georgoulis, Luc Van Gool
2021 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
To capture the cross-task relationships, we propose a neural network architecture that contains task-specific and cross-task refinement heads.  ...  Motivated by this observation, we propose a novel Cross-Task Relation Layer (CTRL), which encodes task dependencies between the semantic and depth predictions.  ...  We thank Amazon Activate for EC2 credits and the anonymous reviewers for the valuable feedback and time spent.  ... 
doi:10.1109/cvpr46437.2021.00810 fatcat:yfbe7ybq75df3dwb33pvsbqagu

Recommender Systems Based on Generative Adversarial Networks: A Problem-Driven Perspective [article]

Min Gao, Junwei Zhang, Junliang Yu, Jundong Li, Junhao Wen, Qingyu Xiong
2020 arXiv   pre-print
More specifically, we propose a taxonomy of these models, along with their detailed descriptions and advantages. Finally, we elaborate on several open issues and current trends in GAN-based RSs.  ...  To gain a comprehensive understanding of these research efforts, we review the corresponding studies and models, organizing them from a problem-driven perspective.  ...  Thus, the generator and discriminator can compete with each other, to improve model explainability. • Cross-Domain Recommendation Based on GANs.  ... 
arXiv:2003.02474v3 fatcat:wemc7k5mujhrdnmxya5pvt2awi

Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developments [article]

Xiaoxu Li, Xiaochen Yang, Zhanyu Ma, Jing-Hao Xue
2022 arXiv   pre-print
We conclude this review with a discussion on current challenges and future trends in few-shot image classification.  ...  Few-shot image classification is a challenging problem that aims to achieve the human level of recognition based only on a small number of training images.  ...  helps learn discriminative features.  ... 
arXiv:2105.08149v2 fatcat:yxsvfdspbrhfpcrzgnny27vgjy

Class-Aware Domain Adaptation for Improving Adversarial Robustness [article]

Xianxu Hou, Jingxin Liu, Bolei Xu, Xiaolong Wang, Bozhi Liu, Guoping Qiu
2020 arXiv   pre-print
Recent works have demonstrated convolutional neural networks are vulnerable to adversarial examples, i.e., inputs to machine learning models that an attacker has intentionally designed to cause the models  ...  Specifically, we propose to learn domain-invariant features for adversarial examples and clean images via a domain discriminator.  ...  One pixel attack [12] is introduced by modifying only one pixel based on differential evolution. Simple rotating 2D images [13] are also used to fool neural network-based vision systems.  ... 
arXiv:2005.04564v1 fatcat:jjwb6v2m6rdy3g7hz7ertesj44
« Previous Showing results 1 — 15 out of 3,194 results