{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T16:32:25Z","timestamp":1792254745987,"version":"4.4.0"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012389","name":"National Institute of Information and Communications Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012389","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000646","name":"JSPS KAKENHI","doi-asserted-by":"publisher","award":["JP19H04166"],"award-info":[{"award-number":["JP19H04166"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892068","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-8","source":"Crossref","is-referenced-by-count":3,"title":["DJMix: Unsupervised Task-agnostic Image Augmentation for Improving Robustness of Convolutional Neural Networks"],"prefix":"10.1109","author":[{"given":"Ryuichiro","family":"Hataya","sequence":"first","affiliation":[{"name":"The University of Tokyo,Graduate School of Information Science and Technology,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hideki","family":"Nakayama","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Graduate School of Information Science and Technology,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Learning Multiple Layers of Features from Tiny Images","author":"krizhevsky","year":"2009","journal-title":"University of Toronto Tech Rep"},{"key":"ref38","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","author":"razavi","year":"2019","journal-title":"NeurIPS"},{"key":"ref33","article-title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","author":"hendrycks","year":"2020","journal-title":"ICLRE"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref31","article-title":"Imagenet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","author":"geirhos","year":"2019","journal-title":"ICLRE"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00871"},{"key":"ref37","article-title":"PyTorch: An Imperative Style, High- Performance Deep Learning Library","author":"paszke","year":"2019","journal-title":"NeurIPS"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3390\/e22101081"},{"key":"ref35","article-title":"Deep variational information bottleneck","author":"alemi","year":"2017","journal-title":"ICLRE"},{"key":"ref34","article-title":"The information bottleneck method","author":"tishby","year":"0","journal-title":"The 37th Annual Allerton Conference on Communication Control and Computing"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2919463"},{"key":"ref40","article-title":"The Pascal Visual Object Classes Chal-lenge: A Retrospective","author":"everingham","year":"2015","journal-title":"ICCV"},{"key":"ref11","article-title":"To-wards achieving adversarial robustness by enforcing feature consistency across bit planes","author":"addepalli","year":"2020","journal-title":"CVPR"},{"key":"ref12","article-title":"Neural Discrete Representation Learning","author":"van den oord","year":"2017","journal-title":"NIPS"},{"key":"ref13","article-title":"Using Videos to Evaluate Image Model Robustness","author":"gu","year":"2019","journal-title":"ArXiv"},{"key":"ref14","article-title":"Towards Deep Learning Models Resistant to Adversarial Attacks","author":"madry","year":"2018","journal-title":"ICLRE"},{"key":"ref15","article-title":"Generalisation in humans and deep neural networks","author":"geirhos","year":"2018","journal-title":"NeurIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref18","article-title":"Making convolutional networks shift-invariant again","author":"zhang","year":"2019","journal-title":"ICML"},{"key":"ref19","article-title":"ImageNet Classification with Deep Convolutional Neural Networks","author":"krizhevsky","year":"2012","journal-title":"NIPS"},{"key":"ref28","article-title":"Measuring the tendency of cnns to learn surface statistical regularities","author":"jo","year":"2017","journal-title":"ArXiv"},{"key":"ref4","article-title":"Benchmarking neural network robust-ness to common corruptions and perturbations","author":"hendrycks","year":"2019","journal-title":"ICLRE"},{"key":"ref27","article-title":"Augmax: Adversarial composition of random augmentations for robust training","author":"wang","year":"2021","journal-title":"NeurIPS"},{"key":"ref3","article-title":"Examining the Impact of Blur on Recognition by Convolutional Networks","author":"vasiljevic","year":"2016","journal-title":"ArXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/83.862633"},{"key":"ref29","article-title":"Adversarial examples are not bugs, they are features","author":"ilyas","year":"2019","journal-title":"NeurIPS"},{"key":"ref5","author":"cover","year":"1999","journal-title":"Elements of Information Theory"},{"key":"ref8","article-title":"Towards under-standing limitations of pixel discretization against adversarial attacks","author":"chen","year":"0","journal-title":"2019 IEEE European Symposium on Security and Privacy (EuroS&P)"},{"key":"ref7","article-title":"Thermometer encoding: One hot way to resist adversarial examples","author":"buckman","year":"2018","journal-title":"ICLRE"},{"key":"ref2","article-title":"Explaining and Harnessing Adversarial Examples","author":"goodfellow","year":"2014","journal-title":"ArXiv"},{"key":"ref9","article-title":"Defending against whitebox adversarial attacks via randomized discretization","author":"zhang","year":"2019","journal-title":"AISTATS"},{"key":"ref1","article-title":"Intriguing properties of neural networks","author":"szegedy","year":"2014","journal-title":"ICLRE"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref45","article-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","author":"ren","year":"2015","journal-title":"NIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00575"},{"key":"ref21","article-title":"mixup: Beyond Empirical Risk Minimization","author":"zhang","year":"2018","journal-title":"ICLRE"},{"key":"ref42","article-title":"Benchmarking robustness in object detection: Autonomous driving when winter is coming","author":"michaelis","year":"2019","journal-title":"ArXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"ref23","article-title":"Improved Regularization of Convolutional Neural Networks with Cutout","author":"devries","year":"0","journal-title":"ArXiv"},{"key":"ref44","article-title":"Rethinking Atrous Convolution for Semantic Image Segmentation","author":"chen","year":"2017","journal-title":"ArXiv"},{"key":"ref26","article-title":"A fourier perspective on model robustness in computer vision","author":"yin","year":"2019","journal-title":"NeurIPS"},{"key":"ref43","article-title":"Wide Residual Networks","author":"zagoruyko","year":"2016","journal-title":"BMVC"},{"key":"ref25","article-title":"Auto aug-ment: Learning augmentation strategies from data","author":"cubuk","year":"2019","journal-title":"CVPR"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","location":"Padua, Italy","start":{"date-parts":[[2022,7,18]]},"end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892068.pdf?arnumber=9892068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T20:52:48Z","timestamp":1665780768000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892068\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892068","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}