计算机科学 ›› 2024, Vol. 51 ›› Issue (1): 150-167.doi: 10.11896/jsjkx.230500103
孙书魁1,2, 范菁1,2, 孙中强3, 曲金帅1,2, 代婷婷1,2
SUN Shukui1,2, FAN Jing1,2, SUN Zhongqing3, QU Jinshuai1,2, DAI Tingting1,2
摘要: 近年来,深度学习在图像分类、目标检测、图像分割等诸多计算机视觉任务中都取得了出色的性能表现。深度神经网络通常依靠大量的训练数据来避免过拟合,因此,出色的性能背后离不开海量图像数据的支持。但在很多实际应用场景中,通常很难获取到足够的图像数据,并且数据的收集也是昂贵且耗时的。图像数据增强的出现很好地缓解了数据不足的问题,作为增加训练数量、提升数据质量和多样性的有效途径,数据增强已成为深度学习模型在图像数据上成功应用的必要组成部分,理解现有算法有助于选择适合的方法以及开发新算法。文中阐述了图像数据增强的研究动机,对众多的数据增强算法进行了系统分类,详细分析了每一类数据增强算法;随后指出数据增强算法设计时的一些注意事项及其应用范围,并通过3种计算机视觉任务证明了数据增强的有效性;最后总结全文并对数据增强未来的研究方向进行展望。
中图分类号:
[1]LITJENS G,KOOI T,BEJNORDI B E,et al.A survey on deep learning in medical image analysis[J].Medical Image Analysis,2017,42:60-88. [2]XU M,YOON S,FUENTES A,et al.Style-consistent imagetranslation:a novel data augmentation paradigm to improve plant disease recognition[J].Frontiers in Plant Science,2022,12:3361. [3]WONG S C,GATT A,STAMATESCU V,et al.Understanding data augmentation for classification:when to warp?[C]//Proceedings of the 2016 International Conference on Digital Image Computing:Techniques and Applications(DICTA).IEEE,2016. [4]SHORTEN C,KHOSHGOFTAAR T M.A survey on image data augmentation for deep learning[J].Journal of big data,2019,6(1):1-48. [5]SAINI D,MALIK R.Image Data Augmentation techniques for Deep Learning-A Mirror Review[C]//Proceedings of the 2021 9th International Conference on Reliability,Infocom Technologies and Optimization(Trends and Future Directions)(ICRITO).IEEE,2021. [6]NANNI L,PACI M,BRAHNAM S,et al.Comparison of diffe-rent image data augmentation approaches[J].Journal of Imaging,2021,7(12):254. [7]HUANG S Y,WU W,YANG Y,et al.A Low-Exposure Image Enhancement Based on Progressive Dual Network Model[J].Chinese Journal of Computers,2021,44(2):384-394. [8]DABLAIN D,KRAWCZYK B,CHAWLA N V.DeepSMOTE:Fusing deep learning and SMOTE for imbalanced data[J].IEEE Transactions on Neural Networks and Learning Systems,2022,9(34):6390-6404. [9]TOMMASI T,LANZI M,RUSSO P,et al.Learning the roots ofvisual domain shift[C]//Proceedings of the Computer Vision.ECCV,2016. [10]ZHANG C,BENGIO S,HARDT M,et al.Understanding deep learning(still) requires rethinking generalization[J].Communications of the ACM,2021,64(3):107-15. [11]KHALIFA N E,LOEY M,MIRJALILI S.A comprehensivesurvey of recent trends in deep learning for digital images augmentation[J].Artificial Intelligence Review,2022,55:2351-2377. [12]CORDTS M,OMRAN M,RAMOS S,et al.The cityscapes dataset for semantic urban scene understanding[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016. [13]HE K,ZHANG X,REN S,et al.Deep residual learning forimage recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016. [14]HUANG G,LIU Z,VAN DER MAATEN L,et al.Densely con-nected convolutional networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017. [15]WANG C Y,BOCHKOVSKIY A,LIAO H Y.Scaled-yolov4:Scaling cross stage partial network[C]//Proceedings of the IEEE/cvf Conference on Computer Vision and Pattern Recognition.2021. [16]MA W,WU Y,CEN F,et al.Mdfn:Multi-scale deep featurelearning network for object detection[J].Pattern Recognition,2020,100:107149. [17]ZHU J Y,PARK T,ISOLA P,et al.Unpaired image-to-imagetranslation using cycle-consistent adversarial networks[C]//Proceedings of the IEEE International Conference on Computer Vision.2017. [18]XU W,SHAWN K,WANG G.Toward learning a unified many-to-many mapping for diverse image translation[J].Pattern Re-cognition,2019,93:570-80. [19]SINGH K K,LEE Y J.Hide-and-seek:Forcing a network to be meticulous for weakly-supervised object and action localization[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision(ICCV).IEEE,2017. [20]DEVRIES T,TAYLOR G W.Improved regularization of convolutional neural networks with cutout[J].arXiv:1708.04552,2017. [21]ZHONG Z,ZHENG L,KANG G,et al.Random erasing dataaugmentation[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020. [22]CHEN P,LIU S,ZHAO H,et al.Gridmask data augmentation[J].arXiv:2001.04086,2020. [23]VAPNIK V.Principles of risk minimization for learning theory[J].Advances in Neural Information Processing Systems,1991,4:831-838. [24]INOUE H.Data augmentation by pairing samples for imagesclassification[J].arXiv:1801.02929,2018. [25]ZHANG H,CISSE M,DAUPHIN Y N,et al.mixup:Beyondempirical risk minimization[J].arXiv:1710.09412,2017. [26]TOKOZUME Y,USHIKU Y,HARADA T.Between-classlearning for image classification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018. [27]YUN S,HAN D,OH S J,et al.Cutmix:Regularization strategy to train strong classifiers with localizable features[C]//Procee-dings of the IEEE/CVF International Conference on Computer Vision.2019. [28]BOCHKOVSKIY A,WANG C Y,LIAO H Y.Yolov4:Opti-mal speed and accuracy of object detection[J].arXiv:2004.10934,2020. [29]HENDRYCKS D,MU N,CUBUK E D,et al.Augmix:A simple method to improve robustness and uncertainty under data shift[C]//Proceedings of the International Conference on Learning Representations.2020. [30]KIM J H,CHOO W,SONG H O.Puzzle mix:Exploiting saliency and local statistics for optimal mixup[C]//proceedings of the International Conference on Machine Learning.2020. [31]KIM J H,CHOO W,JEONG H,et al.Co-mixup:Saliencyguided joint mixup with supermodular diversity[J].arXiv:2102.03065,2021. [32]DABOUEI A,SOLEYMANI S,TAHERKHANI F,et al.Supermix:Supervising the mixing data augmentation[C]//Procee-dings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021. [33]BAEK K,BANG D,SHIM H.GridMix:Strong regularizationthrough local context mapping[J].Pattern Recognition,2021,109:107594. [34]DWIBEDI D,MISRA I,HEBERT M.Cut,paste and learn:Surprisingly easy synthesis for instance detection[C]//Proceedings of the IEEE International Conference on Computer Vision.2017. [35]DVORNIK N,MAIRAL J,SCHMID C.Modeling visual context is key to augmenting object detection datasets[C]//Proceedings of the European Conference on Computer Vision(ECCV).2018. [36]GHIASI G,CUI Y,SRINIVAS A,et al.Simple copy-paste is a strong data augmentation method for instance segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021. [37]XU Z,MENG A,SHI Z,et al.Continuous copy-paste for one-stage multi-object tracking and segmentation[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2021. [38]YANG J.Gridmask based data augmentation for bengali handwritten grapheme classification[C]//Proceedings of the 2020 2nd International Conference on Intelligent Medicine and Image Processing.2020. [39]GOODFELLOW I,POUGET-ABADIE J,MIRZA M,et al.Ge-nerative adversarial networks[J].Communications of the ACM,2020,63(11):139-44. [40]RADFORD A,METZ L,CHINTALA S.Unsupervised representation learning with deep convolutional generative adversarial networks[J].arXiv:1511.06434,2015. [41]MADANI A,MORADI M,KARARGYRIS A,et al.Chest x-ray generation and data augmentation for cardiovascular abnormality classification[C]//Proceedings of the Medical Imaging.SPIE,2018. [42]FRID-ADAR M,KLANG E,AMITAI M,et al.Synthetic data augmentation using GAN for improved liver lesion classification[C]//Proceedings of the 2018 IEEE 15th International Symposium on Biomedical Imaging(ISBI 2018).IEEE,2018. [43]FRID-ADAR M,DIAMANT I,KLANG E,et al.GAN-basedsynthetic medical image augmentation for increased CNN performance in liver lesion classification[J].Neurocomputing,2018,321:321-31. [44]TRAN T,PHAM T,CARNEIRO G,et al.A bayesian data augmentation approach for learning deep models[J].Advances in neural information processing systems,2017,12:1-10. [45]DOUZAS G,BACAO F.Effective data generation for imba-lanced learning using conditional generative adversarial networks[J].Expert Systems with Applications,2018,91:464-471. [46]MARIANI G,SCHEIDEGGER F,ISTRATE R,et al.Bagan:Data augmentation with balancing gan[J].arXiv:1803.09655,2018. [47]ANTONIOU A,STORKEY A,EDWARDS H.Data augmentation generative adversarial networks[J].arXiv:1711.04340,2017. [48]ALI-GOMBE A,ELYAN E.MFC-GAN:Class-imbalanced data-set classification using multiple fake class generative adversarial network[J].Neurocomputing,2019,361:212-221. [49]YANG H,ZHOU Y.Ida-gan:A novel imbalanced data augmentation gan[C]//Proceedings of the 2020 25th International Conference on Pattern Recognition(ICPR),IEEE,2021. [50]HUANG SW,LIN CT,CHEN SP,et al.Auggan:Cross domain adaptation with gan-based data augmentation[C]//Proceedings of the European Conference on Computer Vision(ECCV).2018. [51]ZHU Y,AOUN M,KRIJN M,et al.Data Augmentation using Conditional Generative Adversarial Networks for Leaf Counting in Arabidopsis Plants[C]//Proceedings of the BMVC.2018. [52]GEIRHOS R,RUBISCH P,MICHAELIS C,et al.ImageNet-trained CNNs are biased towards texture;increasing shape bias improves accuracy and robustness[J].arXiv:1811.12231,2018. [53]ZHU X,LIU Y,LI J,et al.Emotion classification with data augmentation using generative adversarial networks[C]//Procee-dings of the Advances in Knowledge Discovery and Data Mining:22nd Pacific-Asia Conference(PAKDD 2018).Melbourne,VIC,Australia,Part III 22.Springer,2018. [54]SCHWARTZ E,KARLINSKY L,SHTOK J,et al.Delta-en-coder:an effective sample synthesis method for few-shot object recognition[J].Advances in Neural Information Processing Systems,2018,31:2850-2860. [55]HONG M,CHOI J,KIM G.Stylemix:Separating content andstyle for enhanced data augmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021. [56]DUMOULIN V,SHLENS J,KUDLUR M.A learned representation for artistic style[J].arXiv:1610.07629,2016. [57]HUANG X,BELONGIE S.Arbitrary style transfer in real-time with adaptive instance normalization[C]//Proceedings of the IEEE International Conference on Computer Vision.2017. [58]SHRIVASTAVA A,PFISTER T,TUZEL O,et al.Learningfrom simulated and unsupervised images through adversarial training[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017. [59]LEE H Y,TSENG H Y,MAO Q,et al.Drit++:Diverse image-to-image translation via disentangled representations[J].International Journal of Computer Vision,2020,128:2402-2417. [60]PARK T,LIU MY,WANG TC,et al.Semantic image synthesis with spatially-adaptive normalization[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019. [61]JACKSON P T,ABARGHOUEI A A,BONNER S,et al.Style augmentation:data augmentation via style randomization[C]//Proceedings of the CVPR Workshops.2019. [62]FONTANINI T,IOTTI E,DONATI L,et al.MetalGAN:Multi-domain label-less image synthesis using cGANs and meta-lear-ning[J].Neural Networks,2020,131:185-200. [63]LI Y,YU Q,TAN M,et al.Shape-texture debiased neural network training[J].arXiv:2010.05981,2020. [64]FAWZI A,SAMULOWITZ H,TURAGA D,et al.Adaptive data augmentation for image classification[C]//Proceedings of the 2016 IEEE International Conference on Image Processing(ICIP).IEEE 2016. [65]CUBUK E D,ZOPH B,MANE D,et al.Autoaugment:Learning augmentation strategies from data[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019. [66]LIM S,KIM I,KIM T,et al.Fast autoaugment[J].Advances in Neural Information Processing Systems,2019,32:6665-6675. [67]HO D,LIANG E,CHEN X,et al.Population based augmentation:Efficient learning of augmentation policy schedules[C]//Proceedings of the International Conference on Machine Lear-ning.PMLR,2019. [68]HATAYA R,ZDENEK J,YOSHIZOE K,et al.Faster autoaugment:Learning augmentation strategies using backpropagation[C]//Proceedings of the Computer Vision.Springer,2020. [69]CUBUK E D,ZOPH B,SHLENS J,et al.Randaugment:Practical automated data augmentation with a reduced search space[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops.2020. [70]HATAYA R,ZDENEK J,YOSHIZOE K,et al.Meta approach to data augmentation optimization[C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision.2022. [71]ZOPH B,CUBUK E D,GHIASI G,et al.Learning data augmentation strategies for object detection[C]//Proceedings of the Computer Vision.Springer,2020. [72]RATNER A J,EHRENBERG H,HUSSAIN Z,et al.Learning to compose domain-specific transformations for data augmentation[J].Advances in Neural Information Processing Systems,2017,30:3236-3246. [73]TANG Z,PENG X,LI T,et al.Adatransform:Adaptive data transformation[C]//Proceedings of the IEEE/CVF Interna-tional Conference on Computer Vision.2019. [74]ZHANG X,WANG Q,ZHANG J,et al.Adversarial autoaugment[J].arXiv:1912.11188,2019. [75]LEE D,PARK H,PHAM T,et al.Learning augmentation network via influence functions[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020. [76]TAKASE T,KARAKIDA R,ASOH H.Self-paced data aug-mentation for training neural networks[J].Neurocomputing,2021,442:296-306. [77]SCHULMAN J,WOLSKI F,DHARIWAL P,et al.Proximalpolicy optimization algorithms[J].arXiv:1707.06347,2017. [78]LEMLEY J,BAZRAFKAN S,CORCORAN P.Smart augmentation learning an optimal data augmentation strategy[J].IEEE Access,2017,5:5858-5869. [79]XU B,ZHANG L,MAO Z,et al.Curriculum learning for natural language understanding[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.2020. [80]GENG F H,LIU H,GUO Q,et al.Variational Optical Flow Estimation Based Super-Resolution Reconstruction for Lung 4D-CT Image[J].Journal of Computer Research and Development,2017,54(08):1703-1712. [81]CHEN K R,MENG X F.Interpretation and Understanding inMachine Learning[J].Journal of Computer Research and Deve-lopment,2017,54(08):1703-1712. [82]LIU Q X,WANG J N,YIN J,et al.Application of adversarial machine learning in network intrusion detection[J].Journal on Communications,2021,42(11):1-12. [83]LI Z T,SUN J B,YANG K W,et al.A Review of Adversarial Robustness Evaluation for Image Classification[J].Journal of Computer Research and Development,2022,59(10):2164-2189. [84]LIU B,ZENG Q,LU L,et al.A survey of recommendation systems based on deep learning[C]//Proceedings of the Journal of Physics:Conference Series.2021. [85]ZHAO H,SHI J,QI X,et al.Pyramid scene parsing network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017. [86]CAO Y,XU J,LIN S,et al.Gcnet:Non-local networks meet squeeze-excitation networks and beyond[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops.2019. [87]HUANG L,YUAN Y,GUO J,et al.Interlaced sparse self-attention for semantic segmentation[J].arXiv:1907.12273,2019. [88]ZAGORUYKO S,KOMODAKIS N.Wide residual networks[J].arXiv:1605.07146,2016. [89]GASTALDI X.Shake-shake regularization[J].arXiv:1705.07485,2017. [90]REN S,HE K,GIRSHICK R,et al.Faster r-cnn:Towards real-time object detection with region proposal networks[J].Advances in neural information processing systems,2015,28:91-99. [91]DUAN K,BAI S,XIE L,et al.Centernet:Keypoint triplets for object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2019. [92]CHUQUICUSMA M J,HUSSEIN S,BURT J,et al.How tofool radiologists with generative adversarial networks? A visual turing test for lung cancer diagnosis[C]//Proceedings of the 2018 IEEE 15th International Symposium on Biomedical Imaging.IEEE,2018. [93]BERMUDEZ C,PLASSARD A J,DAVIS L T,et al.Learning implicit brain MRI manifolds with deep learning[C]//Procee-dings of the Medical Imaging 2018:Image Processing.SPIE,2018. [94]GHOSH S K,GHOSH A.ENResNet:A novel residual neural network for chest X-ray enhancement based COVID-19 detection[J].Biomedical Signal Processing and Control,2022,72:103286. [95]ZHANG S J,PENG Z,LI HUI.SAU-Net:Medical Image Segmentation Method Based on U-Net and Self-Attention[J].Acta Electronica Sinica,2022,50(10):2433-2442. [96]BARSHOOI A H,AMIRKHANI A.A novel data augmentation based on Gabor filter and convolutional deep learning for improving the classification of COVID-19 chest X-Ray images[J].Biomedical Signal Processing and Control,2022,72:103326. [97]LIAO H B,XU B.Robust Face ExpressionRecognition Based on Gender and Age Factor Analysis[J].Journal of Computer Research and Development,2021,58(3):528-538. [98]LOPES A T,DE AGUIAR E,OLIVEIRA-SANTOS T.A facial expression recognition system using convolutional networks[C]//Proceedings of the 2015 28th SIBGRAPI Conference on Graphics,Patterns and Images.IEEE,2015. [99]PITALOKA D A,WULANDARI A,BASARUDDIN T,et al.Enhancing CNN with preprocessing stage in automatic emotion recognition[J].Procedia Computer Science,2017,116:523-529. [100]ZHANG W L,CHEN Y,YANG K W,et al.n Adversarial Example Generation Method for Locally Occluded Face Recognition[J].Journal of Computer Research and Development,2023,60(9):2067-2079. [101]CHOI Y,CHOI M,KIM M,et al.Stargan:Unified generativeadversarial networks for multi-domain image-to-image translation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018. [102]HOU R B,CHANG H,MA B P,et al.Temporal Multi-Scale Complementary Feature for Video Person Re-Identification[J].Chinese Journal of Computers,2023,46(1):31-50. [103]ZHONG Z,ZHENG L,ZHENG Z,et al.Camstyle:A novel data augmentation method for person re-identification[J].IEEE Transactions on Image Processing,2018,28(3):1176-1190. [104]YANG W X,YAN Y,CHEN S,et al.Multi-scale Generative Adversarial Network for Person Re- identification under Occlusion[J].Journal of Software,2020,31(7):1943-1958. [105]CHEN F,WANG N,TANG J,et al.Self-supervised data augmentation for person re-identification[J].Neurocomputing,2020,415:48-59. [106]ZHOU F,SHU H F,BAI M L,et al.Cross-Modal Person Re-identification Based on Generative Adversarial Network Coordinated with Angle Based Heterogeneous Center Triplet Loss[J].Acta Electronica Sinica,2023,51(7):1803-1811. [107]JIA X,ZHONG X,YE M,et al.Complementary Data Augmentation for Cloth-Changing Person Re-Identification[J].IEEE Transactions on Image Processing,2022,31:4227-4239. [108]REN X N,ZHANG D M,BAO X G,et al.Semantic guidance attention network for occluded person re-identification[J].Journal on Communications,2021,42(10):106-116. [109]BARGOTI S,UNDERWOOD J.Deep fruit detection in orchards[C]//Proceedings of the 2017 IEEE International Conference on Robotics and Automation(ICRA).IEEE,2017. [110]GHAZI M M,YANIKOGLU B,APTOULA E.Plant identification using deep neural networks via optimization of transfer learning parameters[J].Neurocomputing,2017,235:228-235. [111]KHALIFA N E M,LOEY M,TAHA M H N.Insect pests re-cognition based on deep transfer learning models[J].J Theor Appl Inf Technol,2020,98(1):60-68. [112]VALERIO GIUFFRIDA M,SCHARR H,TSAFTARIS S A.Arigan:Synthetic arabidopsis plants using generative adversa-rial network[C]//Proceedings of the IEEE International Confe-rence on Computer Vision Workshops.2017. [113]ZHANG Y D,DONG Z,CHEN X,et al.Image based fruit category classification by 13-layer deep convolutional neural network and data augmentation[J].Multimedia Tools and Applications,2019,78:3613-3632. [114]YAN Y,ZHANG Y,SU N.A novel data augmentation method for detection of specific aircraft in remote sensing RGB images[J].IEEE Access,2019,7:56051-56061. [115]GUIRADO E,TABIK S,RIVAS M L,et al.Whale counting in satellite and aerial images with deep learning[J].Scientific Reports,2019,9(1):14259. [116]SHAWKY O A,HAGAG A,EL-DAHSHAN ES A,et al.Remote sensing image scene classification using CNN-MLP with data augmentation[J].Optik,2020,221:165356. [117]YAMASHKIN S A,YAMASHKIN A A,ZANOZIN V V,et al.Improving the efficiency of deep learning methods in remote sensing data analysis:geosystem approach[J].IEEE Access,2020,8:179516-179529. [118]EITEL A,SPRINGENBERG J T,SPINELLO L,et al.Multimodal deep learning for robust RGB-D object recognition[C]//Proceedings of the 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS).IEEE,2015. [119]FARFADE S S,SABERIAN M J,LI LJ.Multi-view face detection using deep convolutional neural networks[C]//Proceedings of the 5th ACM on International Conference on Multimedia Retrieval.2015. [120]YU Q,YANG Y,SONG YZ,et al.Sketch-a-net that beats humans[J].arXiv:1501.07873,2015. [121]BOOMINATHAN L,KRUTHIVENTI S S,BABU R V.Crowdnet:A deep convolutional network for dense crowd counting[C]//Proceedings of the 24th ACM International Conference on Multimedia.2016. [122]UHLICH S,PORCU M,GIRON F,et al.Improving musicsource separation based on deep neural networks through data augmentation and network blending[C]//Proceedings of the 2017 IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP).IEEE,2017. [123]KHALIFA N E,TAHA M H,HASSANIEN A E,et al.Deep galaxy V2:Robust deep convolutional neural networks for ga-laxy morphology classifications[C]//Proceedings of the 2018 International Conference on Computing Sciences and Engineering(ICCSE).IEEE,2018. [124]LIM S K,LOO Y,TRAN N T,et al.Doping:Generative dataaugmentation for unsupervised anomaly detection with GAN[C]//Proceedings of the 2018 IEEE International Conference on Data Mining(ICDM).IEEE,2018. [125]LOEY M,MANOGARAN G,TAHA M H N,et al.Fightingagainst COVID-19:A novel deep learning model based on YOLO-v2 with ResNet-50 for medical face mask detection[J].Sustainable cities and society,2021,65:102600. [126]LOEY M,MANOGARAN G,TAHA M H N,et al.A hybrid deep transfer learning model with machine learning methods for face mask detection in the era of the COVID-19 pandemic[J].Measurement,2021,167:108288. [127]SALIMANS T,GOODFELLOW I,ZAREMBA W,et al.Im-proved techniques for training gans[J].Advances in Neural Information Processing Systems,2016,29:2234-2242. [128]LIU Y,TIAN W,LI S.Meta-data Augmentation Based Search Strategy Through Generative Adversarial Network for AutoML Model Selection[C]//Proceedings of the Advances in Know-ledge Discovery and Data Mining.2021. [129]WANG Y,HUANG G,SONG S,et al.Regularizing deep networks with semantic data augmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2021,44(7):3733-3748. [130]WANG Q,MENG F,BRECKON T P.Data augmentation with norm-vae for unsupervised domain adaptation[J].arXiv:2012.00848,2020. [131]VERMA V,LAMB A,BECKHAM C,et al.Manifold mixup:Better representations by interpolating hidden states[C]//Proceedings of the International Conference on Machine Learning.2019. [132]CEN F,ZHAO X,LI W,et al.Deep feature augmentation for occluded image classification[J].Pattern Recognition,2021,111:107737. [133]CAO H,TAN C,GAO Z,et al.A survey on generative diffusion model[J].arXiv:2209.02646,2022. [134]RAMESH A,PAVLOV M,GOH G,et al.Zero-shot text-to-image generation[C]//Proceedings of the International Confe-rence on Machine Learning.2021. [135]SAHARIA C,CHAN W,SAXENA S,et al.Photorealistic text-to-image diffusion models with deep language understanding[J].Advances in Neural Information Processing Systems,2022,35:36479-36494. [136]YU J,XU Y,KOH J Y,et al.Scaling autoregressive models for content-rich text-to-image generation[J].arXiv:2206.10789,2022. [137]DHARIWAL P,NICHOL A.Diffusion models beat gans onimage synthesis[J].Advances in Neural Information Processing Systems,2021,34:8780-8794. |
|