Filters








2,174 Hits in 4.5 sec

Mastering Sketching: Adversarial Augmentation for Structured Prediction [article]

Edgar Simo-Serra, Satoshi Iizuka, Hiroshi Ishikawa
2017 arXiv   pre-print
We present an integral framework for training sketch simplification networks that convert challenging rough sketches into clean line drawings.  ...  First, because the discriminator network learns the structure in line drawings, it encourages the output sketches of the simplification network to be more similar in appearance to the training sketches  ...  Adversarial Augmentation We present adversarial augmentation, which is the fusion of unsupervised and adversarial training focused on the purpose of augmenting existing networks for structured prediction  ... 
arXiv:1703.08966v1 fatcat:bswjmqf3ajbuzhy52jpwcnqtpi

Cleanup Sketched Drawings: Deep Learning-Based Model

Amal Ahmed Hasan Mohammed, Jiazhou Chen, Fahd Abd Algalil
2022 Applied Bionics and Biomechanics  
From experimental results, it was observed that an enhanced FCNN model reported better accuracy, reducing the prediction error by 0.08 percent for simplifying the rough sketch compared to the existing  ...  For evaluating the results, the mean squared error (MSE) metric was used.  ...  [35] proposed a deep learning system for predicting primitive parametric shapes.  ... 
doi:10.1155/2022/2238077 pmid:35578715 pmcid:PMC9107365 fatcat:5wjndf4nbfhfva3wrjrroku6vy

Lafcadio Hearn's America: ethnographic sketches and editorials

2002 ChoiceReviews  
The population of America will probably never reach the gigantic figure once predicted for it.  ...  To raise money for the trip, Hearn penned some translations for Harper's. On March Sketch by CD.  ... 
doi:10.5860/choice.40-0759 fatcat:gmjnqqwrpbfxlntbam7ty2btxe

Strategy Rule 3. Act with Speed: The Essential Component to Secure a Competitive Lead [chapter]

2007 Mastering the Rules of Competitive Strategy  
Original industry estimates pegged sales at 12 million units, with sales growth predicted at a rate of 74 percent annually for several years.  ...  To heighten enthusiasm in the ranks, Lutz forced design studios to compete in "sketch-offs."  ... 
doi:10.1201/9781420068108-7 fatcat:fput22eernfz7jq5ivwumogakq

Sketch with Artificial Intelligence (AI) - A Multimodal AI Approach for Conceptual Design

Yifan Zhou, Hyoung-June Park
2021 CAADRIA proceedings   unpublished
The goal of the research is to investigate an AI approach to assist architects with multimodal inputs (sketches and textual information) for conceptual design.  ...  A novel machine learning approach for the multimodal input system is introduced and compared to other approaches.  ...  Pix2Pix with a U-net structure (Isola et al., 2017) , a conditional generative adversarial network (cGAN), is combined with procedural training for generating the variations of its predicted image.  ... 
doi:10.52842/conf.caadria.2021.1.201 fatcat:a7o2bfw7tzfnvmq23tfosn5wga

Informative Dropout for Robust Representation Learning: A Shape-bias Perspective [article]

Baifeng Shi, Dinghuai Zhang, Qi Dai, Zhanxing Zhu, Yadong Mu, Jingdong Wang
2020 arXiv   pre-print
Recent work also indicates a close relationship between CNN's texture-bias and its robustness against distribution shift, adversarial perturbation, random corruption, etc.  ...  Through extensive experiments, we observe enhanced robustness under various scenarios (domain generalization, few-shot classification, image corruption, and adversarial perturbation).  ...  The authors are thankful to Tianyuan Zhang, Dejia Xu, Yiwen Guo and the anonymous reviewers for the insightful discussions and useful suggestions.  ... 
arXiv:2008.04254v1 fatcat:laub5usrjnechhxvxh3f3bl3wa

The Origins and Prevalence of Texture Bias in Convolutional Neural Networks [article]

Katherine L. Hermann, Ting Chen, Simon Kornblith
2020 arXiv   pre-print
The effect of data augmentation is much larger.  ...  By taking less aggressive random crops at training time and applying simple, naturalistic augmentation (color distortion, noise, and blur), we train models that classify ambiguous images by shape a majority  ...  Acknowledgments and Disclosure of Funding We thank Jay McClelland, Andrew Lampinen, Akshay Jagadeesh, and Chengxu Zhuang for useful conversations, and Guodong Zhang and Lala Li for comments on an earlier  ... 
arXiv:1911.09071v3 fatcat:b7fkhfftpnearecglfsennxovu

Adversarial Training in Affective Computing and Sentiment Analysis: Recent Advances and Perspectives [Review Article]

Jing Han, Zixing Zhang, Bjorn Schuller
2019 IEEE Computational Intelligence Magazine  
We expect that this overview will help facilitate the development of adversarial training for affective computing and sentiment analysis in both the academic and industrial communities.  ...  As a potentially crucial technique for the development of the next generation of emotional AI systems, we herein provide a comprehensive overview of the application of adversarial training to affective  ...  Examples, to name just a few, include the Sketch-GAN proposed for sketch retrieval [75] , the ArtGAN for artwork synthesis [76] , the SEGAN for speech enhancement [77] , the WaveGAN for raw audio synthesis  ... 
doi:10.1109/mci.2019.2901088 fatcat:edkvfgy3ofgufcytngf5mktpae

Adversarial Training in Affective Computing and Sentiment Analysis: Recent Advances and Perspectives [article]

Jing Han, Zixing Zhang, Nicholas Cummins, Björn Schuller
2018 arXiv   pre-print
We expect that this overview will help facilitate the development of adversarial training for affective computing and sentiment analysis in both the academic and industrial communities.  ...  As a potentially crucial technique for the development of the next generation of emotional AI systems, we herein provide a comprehensive overview of the application of adversarial training to affective  ...  Examples, to name just a few, include the Sketch-GAN proposed for sketch retrieval [75] , the ArtGAN for artwork synthesis [76] , the SEGAN for speech enhancement [77] , the WaveGAN for raw audio synthesis  ... 
arXiv:1809.08927v1 fatcat:m5mencegljgsphub3p62ltrhby

Deep Learning-Based Masonry Wall Image Analysis

Yahya Ibrahim, Balázs Nagy, Csaba Benedek
2020 Remote Sensing  
The first adversarial network predicts the schematic mortar-brick pattern of the occluded areas based on the observed wall structure, providing in itself valuable structural information for archeological  ...  The second adversarial network predicts the pixels' color values yielding a realistic visual experience for the observer.  ...  Figure 14 . 14 Inpainting results with utilizing simple sketch drawings (shown by red in the middle column) created by experts for mortar structure estimation in the occluded regions.  ... 
doi:10.3390/rs12233918 fatcat:urltklyrhjg4pagxaztaqei3ui

SketchPatch: Sketch Stylization via Seamless Patch-level Synthesis [article]

Noa Fish, Lilach Perry, Amit Bermano, Daniel Cohen-Or
2020 pre-print
An adversarial addition promotes generalization and robustness to diverse geometries at inference time, forming a simple and effective system for arbitrary sketch stylization, as demonstrated upon a variety  ...  Lacking the necessary volumes of data for standard training of translation systems, we advocate for operation at the patch level, where a handful of stylized sketches provide ample mining potential for  ...  ACKNOWLEDGEMENTS We are grateful to Idan Gilboa (https://www.idangilboa.com) for creating and sharing many of the art pieces displayed in this paper, and to the anonymous reviewers for their helpful feedback  ... 
doi:10.1145/3414685.3417816 arXiv:2009.02216v1 fatcat:bq5tyspnzze67fxj2sovihqluq

Deep image synthesis from intuitive user input: A review and perspectives

Yuan Xue, Yuan-Chen Guo, Han Zhang, Tao Xu, Song-Hai Zhang, Xiaolei Huang
2021 Computational Visual Media  
AbstractIn many applications of computer graphics, art, and design, it is desirable for a user to provide intuitive non-image input, such as text, sketch, stroke, graph, or layout, and have a computer  ...  While classically, works that allow such automatic image content generation have followed a framework of image retrieval and composition, recent advances in deep generative models such as generative adversarial  ...  National Natural Science Foundation of China (Project Nos. 61521002 and 61772298), a Research Grant of Beijing Higher Institution Engineering Research Center, and the Tsinghua-Tencent Joint Laboratory for  ... 
doi:10.1007/s41095-021-0234-8 fatcat:ot6dyrrrsnakxob4jzw4zld7zu

Augmenting Vascular Disease Diagnosis by Vasculature-aware Unsupervised Learning

Yong WANG, Mengqi JI, Shengwei JIANG, Xukang WANG, Jiamin WU, Feng DUAN, Jingtao FAN, Laiqiang HUANG, Shaohua MA, Lu FANG, Qionghai DAI
2020 biorxiv/medrxiv  
The VasNet adopts the multi-scale fusion strategy with a domain adversarial neural network (DANN) loss function that induces biased pattern reconstruction, by strengthening the features relevant to the  ...  Here, we report VasNet, a vasculature-aware unsupervised learning algorithm that augments pathovascular recognition from small sets of unlabeled fluorescence and digital subtraction angiography (DSA) images  ...  The principle of diagnosis augmentation is sketched in Fig. 1 .  ... 
doi:10.1101/2020.02.07.938282 fatcat:jcatuq53hngz7dojk4ki2x3esq

Generalizing Across Domains via Cross-Gradient Training [article]

Shiv Shankar, Vihari Piratla, Soumen Chakrabarti, Siddhartha Chaudhuri, Preethi Jyothi, Sunita Sarawagi
2018 arXiv   pre-print
In contrast, CROSSGRAD is free to use domain signals for predicting labels, if it can prevent overfitting on training domains.  ...  is a more stable and accurate method than domain adversarial training.  ...  ACKNOWLEDGEMENTS We gratefully acknowledge the support of NVIDIA Corporation with the donation of Titan X GPUs used for this research. We thank Google for supporting travel to the conference venue.  ... 
arXiv:1804.10745v2 fatcat:bzslwe62j5fhnj5chwg6kbx524

New Ideas and Trends in Deep Multimodal Content Understanding: A Review

Wei Chen, Weiping Wang, Li Liu, Michael S. Lew
2020 Neurocomputing  
Finally, we include several promising directions for future research.  ...  , including auto-encoders, generative adversarial nets and their variants.  ...  Recent representative network structures for multimodal feature learning are auto-encoders and generative adversarial networks.  ... 
doi:10.1016/j.neucom.2020.10.042 fatcat:hyjkj5enozfrvgzxy6avtbmoxu
« Previous Showing results 1 — 15 out of 2,174 results