Filters








141 Hits in 5.6 sec

Multi-task GANs for Semantic Segmentation and Depth Completion with Cycle Consistency [article]

Chongzhen Zhang, Yang Tang, Chaoqiang Zhao, Qiyu Sun, Zhencheng Ye, Jürgen Kurths
2020 arXiv   pre-print
Extensive experiments on Cityscapes dataset and KITTI depth completion benchmark show that the Multi-task GANs are capable of achieving competitive performance for both semantic segmentation and depth  ...  In this paper, we propose multi-task generative adversarial networks (Multi-task GANs), which are not only competent in semantic segmentation and depth completion, but also improve the accuracy of depth  ...  In this paper, we propose Multitask GANs, which do not share the network layer for semantic segmentation and depth completion.  ... 
arXiv:2011.14272v1 fatcat:imobh7urx5cxxgzhm4h2dyhmai

When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey

Chongzhen Zhang, Jianrui Wang, Gary G. Yen, Chaoqiang Zhao, Qiyu Sun, Yang Tang, Feng Qian, Jürgen Kurths
2020 Patterns  
segmentation, depth estimation, pedestrian detection, and person re-identification.  ...  With widespread applications of artificial intelligence (AI), the capabilities of the perception, understanding, decision-making, and control for autonomous systems have improved significantly in recent  ...  ACKNOWLEDGMENTS The authors would like to thank the Editor-in-Chief, Scientific Editor, and anonymous referees for their helpful comments and suggestions, which have greatly improved this paper.  ... 
doi:10.1016/j.patter.2020.100050 pmid:33205114 pmcid:PMC7660378 fatcat:vs7wm2yrwjamjbaml36663wvze

When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey [article]

Chongzhen Zhang, Jianrui Wang, Gary G. Yen, Chaoqiang Zhao, Qiyu Sun, Yang Tang, Feng Qian, Jürgen Kurths
2020 arXiv   pre-print
in autonomous systems, including image style transfer, image superresolution, image deblurring/dehazing/rain removal, semantic segmentation, depth estimation, pedestrian detection and person re-identification  ...  With widespread applications of artificial intelligence (AI), the capabilities of the perception, understanding, decision-making and control for autonomous systems have improved significantly in the past  ...  ., semantic segmentation and depth estimation.  ... 
arXiv:2003.12948v3 fatcat:qtmjs74p2vh6thdotbhgebdvoi

LiDARNet: A Boundary-Aware Domain Adaptation Model for Point Cloud Semantic Segmentation [article]

Peng Jiang, Srikanth Saripalli
2021 arXiv   pre-print
We present a boundary-aware domain adaptation model for LiDAR scan full-scene semantic segmentation (LiDARNet).  ...  Additionally, we introduce a new dataset (SemanticUSL[The access address of SemanticUSL:]) for domain adaptation for LiDAR point cloud semantic segmentation.  ...  L bd = λ B BCE L BCE (B S ,B S ) + λ B GAN L GAN (G B , D B , X T , B T ) (6) For the semantic segmentation task, L Seg consist of two parts: L S Seg of source data and L T Seg of target data.  ... 
arXiv:2003.01174v3 fatcat:pidvhfapbfhjbmpeofjdhvl7se

Human Action Recognition in Drone Videos using a Few Aerial Training Examples [article]

Waqas Sultani, Mubarak Shah
2021 arXiv   pre-print
We feed the network with real and game, or real and GAN-generated data in an alternating fashion to obtain an improved action classifier.  ...  .,), and it is not easy to generate good discriminative GAN-generated features for all types of actions, we need to efficiently integrate two dataset sources with few available real aerial training videos  ...  ., Richter et al. (2016) designed a method to automatically gather ground truth data for semantic segmentation and Hong et al. (2018) presented a GAN based approach to use game annotations for semantic  ... 
arXiv:1910.10027v4 fatcat:bhnyg5qzafhvhibkfckffwns3i

DeepLIIF: Deep Learning-Inferred Multiplex ImmunoFluorescence for IHC Quantification [article]

Parmida Ghahremani, Yanyun Li, Arie Kaufman, Rami Vanguri, Noah Greenwald, Michael Angelo, Travis J Hollmann, Saad Nadeem
2021 bioRxiv   pre-print
By creating a multitask deep learning framework referred to as DeepLIIF, we are presenting a single step solution to nuclear segmentation and quantitative single-cell IHC scoring.  ...  The code, trained models, and the resultant embeddings for all the datasets used in this paper will be released at https://github.com/nadeemlab/DeepLIIF.  ...  ACKNOWLEDGEMENTS This project was supported by MSK Cancer Center Support Grant/Core Grant (P30 CA008748) and in part by MSK DigITs Hybrid Research Initiative and NSF grants CNS1650499, OAC1919752, and  ... 
doi:10.1101/2021.05.01.442219 fatcat:ugt6rsfre5b7poymdxooq43thq

2021 Index IEEE Transactions on Image Processing Vol. 30

2021 IEEE Transactions on Image Processing  
Departments and other items may also be covered if they have been judged to have archival value. The Author Index contains the primary entry for each item, listed under the first author's name.  ...  The primary entry includes the coauthors' names, the title of the paper or other item, and its location, specified by the publication abbreviation, year, month, and inclusive pagination.  ...  ., +, TIP 2021 853-867 Generative Partial Multi-View Clustering With Adaptive Fusion and Cycle Consistency.  ... 
doi:10.1109/tip.2022.3142569 fatcat:z26yhwuecbgrnb2czhwjlf73qu

Total Generate: Cycle in Cycle Generative Adversarial Networks for Generating Human Faces, Hands, Bodies, and Natural Scenes [article]

Hao Tang, Nicu Sebe
2021 arXiv   pre-print
We propose a novel and unified Cycle in Cycle Generative Adversarial Network (C2GAN) for generating human faces, hands, bodies, and natural scenes.  ...  Both generators are mutually connected and trained in an end-to-end fashion and explicitly form three cycled subnets, i.e., one image generation cycle and two guidance generation cycles.  ...  ACKNOWLEDGMENTS This work was supported by the EU H2020 AI4Media No. 951911 project, by the Italy-China collaboration project TAL-ENT:2018YFE0118400, and by the PRIN project PREVUE.  ... 
arXiv:2106.10876v1 fatcat:o7eljowhl5aezlz5icjatdppz4

Synthetic Data for Deep Learning [article]

Sergey I. Nikolenko
2019 arXiv   pre-print
First, we discuss synthetic datasets for basic computer vision problems, both low-level (e.g., optical flow estimation) and high-level (e.g., semantic segmentation), synthetic environments and datasets  ...  Second, we discuss in detail the synthetic-to-real domain adaptation problem that inevitably arises in applications of synthetic data, including synthetic-to-real refinement with GAN-based models and domain  ...  simulated images, and there are no cycle consistency losses.  ... 
arXiv:1909.11512v1 fatcat:qquxnw4dfvgmfeztbpdqhr44gy

A single latent channel is sufficient for biomedical image segmentation [article]

Andreas M Kist, Stephan Duerr, Anne Schuetzenberger, Marion Semmler
2021 bioRxiv   pre-print
We provide evidence that the latent space is highly correlated with the glottal area waveform, can be encoded with four bits, and decoded using lean decoders while maintaining a high reconstruction accuracy  ...  Recent advances in using deep neural networks for glottis segmentation allow a fully automatic workflow.  ...  Recently, deep neural networks for semantic segmentation have been utilized for glottis segmentation [8, 9] .  ... 
doi:10.1101/2021.12.10.472122 fatcat:oruwzafdmrevpc43uzmhdwbuda

Generative Adversarial Networks for Image Augmentation in Agriculture: A Systematic Review [article]

Ebenezer Olaniyi, Dong Chen, Yuzhen Lu, Yanbo Huang
2022 arXiv   pre-print
Challenges and opportunities of GANs are discussed for future research.  ...  in the presence of challenges with biological variability and unstructured environments.  ...  Acknowledgement This work was supported in part by Cotton Incorporated award #21-005 and the USDA National Institute of Food and Agriculture Hatch project #1025922.  ... 
arXiv:2204.04707v2 fatcat:wcvmq3vl35fo7on2pqyblbzcku

Road Segmentation for Remote Sensing Images using Adversarial Spatial Pyramid Networks [article]

Pourya Shamsolmoali, Masoumeh Zareapoor, Huiyu Zhou, Ruili Wang, Jie Yang
2020 arXiv   pre-print
To address these problems, we introduce a new model to apply structured domain adaption for synthetic image generation and road segmentation.  ...  Because of the complex background, and high density, most of the existing methods fail to accurately extract a road network that appears correct and complete.  ...  [23] proposed a cycle-consistent domain adaptation model that receives multiple forms of representations while enforcing local and global structural consistency through pixel cycle-consistency and semantic  ... 
arXiv:2008.04021v1 fatcat:rrxxun2eqbfjbajznlgwrtvdqq

Modern Augmented Reality: Applications, Trends, and Future Directions [article]

Shervin Minaee, Xiaodan Liang, Shuicheng Yan
2022 arXiv   pre-print
Augmented reality (AR) is one of the relatively old, yet trending areas in the intersection of computer vision and computer graphics with numerous applications in several areas, from gaming and entertainment  ...  , to education and healthcare.  ...  ACKNOWLEDGMENTS We would like to thank Iasonas Kokkinos, Qi Pan, Lyric Kaplan, and Liz Markman for reviewing this work, and providing very helpful comments and suggestions.  ... 
arXiv:2202.09450v2 fatcat:x436ycnvxnhdpfdvhnxkzgbqce

2021 Index IEEE Transactions on Multimedia Vol. 23

2021 IEEE transactions on multimedia  
Departments and other items may also be covered if they have been judged to have archival value. The Author Index contains the primary entry for each item, listed under the first author's name.  ...  The primary entry includes the coauthors' names, the title of the paper or other item, and its location, specified by the publication abbreviation, year, month, and inclusive pagination.  ...  ., +, TMM 2021 772-783 Hard Pixel Mining for Depth Privileged Semantic Segmentation.  ... 
doi:10.1109/tmm.2022.3141947 fatcat:lil2nf3vd5ehbfgtslulu7y3lq

Artificial Intelligence in Quantitative Ultrasound Imaging: A Review [article]

Boran Zhou, Xiaofeng Yang, Tian Liu
2020 arXiv   pre-print
Quantitative ultrasound (QUS) imaging is a reliable, fast and inexpensive technique to extract physically descriptive parameters for assessing pathologies.  ...  Despite its safety and efficacy, QUS suffers from several major drawbacks: poor imaging quality, inter- and intra-observer variability which hampers the reproducibility of measurements.  ...  Yap et al. used the fully convolutional networks (FCNs) for semantic segmentation of breast lesions on BUS images [141] .  ... 
arXiv:2003.11658v1 fatcat:iujuh7gra5ax7od2gxoo6yrbpe
« Previous Showing results 1 — 15 out of 141 results