{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T14:32:57Z","timestamp":1730212377398,"version":"3.28.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1109\/cvpr52688.2022.01120","type":"proceedings-article","created":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T19:56:41Z","timestamp":1664308601000},"page":"11482-11491","source":"Crossref","is-referenced-by-count":16,"title":["Generating High Fidelity Data from Low-density Regions using Diffusion Models"],"prefix":"10.1109","author":[{"given":"Vikash","family":"Sehwag","sequence":"first","affiliation":[{"name":"Princeton University"}]},{"given":"Caner","family":"Hazirbas","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Albert","family":"Gordo","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Firat","family":"Ozgenel","sequence":"additional","affiliation":[{"name":"Meta AI"}]},{"given":"Cristian Canton","family":"Ferrer","sequence":"additional","affiliation":[{"name":"Princeton University"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Improved techniques for training score-based generative models","author":"song","year":"2020","journal-title":"Neural Information Processing Systems Conference"},{"key":"ref38","article-title":"Generative modeling by estimating gradients of the data distribution","author":"song","year":"2019","journal-title":"Conference and Workshop on Neural Information Pro-cessing Systems"},{"key":"ref33","article-title":"Robust learning meets generative models: Can proxy distributions improve adversarial ro-bustness?","author":"sehwag","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref32","article-title":"Ssd: A unified framework for self-supervised outlier detection","author":"sehwag","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref31","article-title":"Pixelcnn++: Improving the pixelcnn with discretized logistic mixture likeli-hood and other modifications","author":"salimans","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref30","article-title":"Assessing generative models via precision and recall","author":"sajjadi","year":"2018","journal-title":"NeurIPS"},{"key":"ref37","article-title":"Denoising diffusion implicit models","author":"song","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref36","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"sohl-dickstein","year":"2015","journal-title":"Ternational Conference on Machine Learning"},{"key":"ref35","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref34","article-title":"Time for a background check! uncov-ering the impact of background features on deep neu-ral networks","author":"sehwag","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref10","article-title":"Diffusion mod-els beat gans on image synthesis","author":"dhariwal","year":"2021","journal-title":"Neural Information Processing Systems Conference"},{"key":"ref40","first-page":"2818","article-title":"Rethinking the in-ception architecture for computer vision","author":"szegedy","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2979601"},{"key":"ref12","article-title":"Imagenet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","author":"robert","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref13","article-title":"Improving robustness using generated data","author":"gowal","year":"2021","journal-title":"arXivpreprintarXiv 2110 09468"},{"key":"ref14","first-page":"34","author":"grcic","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref17","article-title":"Denoising diffusion probabilistic models","author":"ho","year":"2020","journal-title":"Neural Information Processing Systems Conference"},{"key":"ref18","article-title":"Cascaded diffusion models for high fidelity image generation","author":"jonathan","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref19","article-title":"Gotta go fast when generating data with score-based models","author":"jolicoeur-martineau","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref28","first-page":"14866","article-title":"Generating diverse high-fidelity images with vq-vae-2","author":"razavi","year":"2019","journal-title":"Neural Information Processing Systems Conference"},{"key":"ref4","article-title":"Large scale gan training for high fidelity natural image synthesis","author":"brock","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref27","article-title":"Pytorch: An imper-ative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/342009.335388"},{"key":"ref6","article-title":"Ulfar Erlingsson, Alina Oprea, and Colin Raffel. Extracting training data from large language models","author":"carlini","year":"2021","journal-title":"30th USENIX Security Symposium (USENIX Security 21)"},{"key":"ref29","article-title":"ImageNet Large Scale Visual Recognition Challenge","author":"olga","year":"2015","journal-title":"International Journal of Computer Vision"},{"key":"ref5","first-page":"267","article-title":"The secret sharer: Evalu-ating and testing unintended memorization in neural networks","author":"carlini","year":"2019","journal-title":"28th USENIX Security Symposium ( USENIX Security 19)"},{"key":"ref8","article-title":"Imagenet: A large-scale hierar-chical image database","author":"deng","year":"2009","journal-title":"IEEE Conf Computer Vision and Pattern Recognition"},{"key":"ref7","article-title":"Generating long sequences with sparse transformers","author":"child","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref2","article-title":"Discrimina-tor rejection sampling","author":"azadi","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref9","first-page":"13285","article-title":"Instance selection for gans","volume":"33","author":"devries","year":"2020","journal-title":"Neural Information Processing Systems Conference"},{"key":"ref1","article-title":"Estimating example difficulty using variance of gra-dients","author":"agarwal","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1080\/15376494.2019.1609630"},{"key":"ref20","first-page":"5637","article-title":"Wilds: A benchmark of in- the-wild distribution shifts","author":"koh","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref45","first-page":"586","article-title":"The unreasonable ef-fectiveness of deep features as a perceptual metric","author":"richard","year":"2018","journal-title":"IEEE Conf on Computer vision and Pat-tern Recognition"},{"key":"ref22","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009","journal-title":"Technical Report University of Toronto"},{"key":"ref21","article-title":"On fast sampling of diffusion probabilistic models","author":"kong","year":"2021","journal-title":"ar Xiv preprint"},{"key":"ref42","article-title":"Learning to efficiently sample from diffusion probabilistic models","author":"watson","year":"2021","journal-title":"ar Xiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00264"},{"key":"ref41","first-page":"10506","article-title":"Learning robust global representations by penalizing local predictive power","author":"wang","year":"2019","journal-title":"Advances in Netural Information Processing Systems"},{"key":"ref23","article-title":"A cost-effective method for improving and re-purposing large, pre-trained gans by fine-tuning their class-embeddings","author":"qi","year":"2020","journal-title":"Proceedings of the Asian Conference on Computer Vision"},{"key":"ref44","article-title":"Noise or signal: The role of image backgrounds in object recognition","author":"xiao","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref26","article-title":"Improved denoising diffusion probabilistic models","author":"nichol","year":"2021","journal-title":"International Conference on Machine Learning"},{"journal-title":"pytorch-image-models","year":"2019","author":"wightman","key":"ref43"},{"key":"ref25","article-title":"Do deep generative models know what they don't know?","author":"nalisnick","year":"2018","journal-title":"International Conference on Learning Representations"}],"event":{"name":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","start":{"date-parts":[[2022,6,18]]},"location":"New Orleans, LA, USA","end":{"date-parts":[[2022,6,24]]}},"container-title":["2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9878378\/9878366\/09878507.pdf?arnumber=9878507","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T20:56:03Z","timestamp":1665780963000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9878507\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/cvpr52688.2022.01120","relation":{},"subject":[],"published":{"date-parts":[[2022,6]]}}}