[1] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 60, 84-90(2017).

[2] [2] DEVRIES T, TAYL G W. Improved regularization of convolutional neural wks with cutout[EBOL]. arXiv: 1708.04552, 2017.https:arxiv.gabs1708. 04552.

[3] SRIVASTAVA N, HINTON G, KRIZHEVSKY A et al. Dropout: a simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning Research, 15, 1929-1958(2014).

[4] [4] ZHANG H Y, CISSÉ M, DAUPHIN Y N, et al. Mixup: beyond empirical risk minimization[C]6th International Conference on Learning Representations. Vancouver: ICLR, 2018.

[5] [5] WALAWALKAR D, SHEN Z Q, LIU Z C, et al. Attentive cutmix: An enhanced data augmentation approach f deep learning based image classification[C]ICASSP 2020 2020 IEEE International Conference on Acoustics, Speech Signal Processing. Barcelona: IEEE, 2020: 3642 − 3646.

[6] TAKAHASHI R, MATSUBARA T, UEHARA K. Data augmentation using random image cropping and patching for deep CNNs[J]. IEEE Transactions on Circuits and Systems for Video Technology, 30, 2917-2931(2020).

[7] [7] LIN T Y, ROYCHOWDHURY A, MAJI S. Bilinear CNN models f finegrained visual recognition[C]2015 IEEE International Conference on Computer Vision (ICCV). Santiago: IEEE, 2016: 1449 − 1457.

[8] [8] FU J L, ZHENG H L, TAO M. Look closer to see better: recurrent attention convolutional neural wk f finegrained image recognition[C]2017 IEEE Conference on Computer Vision Pattern Recognition. Honolulu: IEEE, 2017: 4476 − 4484.

[9] [9] WANG Y M, MARIU V I, DAVIS L S. Learning a discriminative filter bank within a CNN f finegrained recognition[C]Proceedings of the 2018 IEEECVF conference on Computer Vision Pattern Recognition. Salt Lake City: IEEE, 2018: 4148 − 4157.

[10] CORNIA M, ABATI D, BARALDI L et al. Attentive models in vision: Computing saliency maps in the deep learning era[J]. Intelligenza Artificiale, 12, 161-175(2018).

[11] [11] LI C Y, YUAN Y C, CAI W D, et al. Robust saliency detection via regularized rom walks ranking[C]2015 IEEE Conference on Computer Vision Pattern Recognition. Boston: IEEE, 2015: 2710 − 2717.

[12] [12] ZHANG X N, WANG T T, QI J Q, et al. Progressive attention guided recurrent wk f salient object detection[C]2018 IEEECVF Conference on Computer Vision Pattern Recognition. Salt Lake City: IEEE, 2018: 714 − 722.

[13] [13] WANG X L, GIRSHICK R, GUPTA A, et al. Nonlocal neural wks[C]2018 IEEECVF Conference on Computer Vision Pattern Recognition. Salt Lake City: IEEE, 2018: 7794 − 7803.

[15] [15] MEI Y Q, FAN Y C, ZHOU Y Q. Image superresolution with nonlocal sparse attention[C]Proceedings of 2021 IEEECVF Conference on Computer Vision Pattern Recognition. Nashville: IEEE, 2021: 3516 − 3525.

[16] [16] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning f image recognition[C]2016 IEEE Conference on Computer Vision Pattern Recognition (CVPR). Las Vegas: IEEE, 2016: 770 − 778.

[17] [17] KIM J H, CHOO W, SONG H O. Puzzle mix: exploiting saliency local statistics f optimal mixup[C]Proceedings of the 37th International Conference on Machine Learning. Vienna, Austria, 2020: 5275 − 5285.

[18] [18] YANG Z, LUO T G, WANG D, et al. Learning to navigate f finegrained classification[C]Proceedings of the 15th European Conference on Computer Vision. Munich: Springer, 2018: 438 − 454.

[19] [19] UDDIN A F M S, MONIRA M S, SHIN W, et al. SaliencyMix: a saliency guided data augmentation strategy f better regularization[C]9th International Conference on Learning Representations. ICLR, Vienna, Austria, 2021.

[20] CHANG D L, DING Y F, XIE J Y et al. The devil is in the channels: mutual-channel loss for fine-grained image classification[J]. IEEE Transactions on Image Processing, 29, 4683-4695(2020).

[21] [21] YE Z H, HU F Y, LIU Y, et al. Associating multiscale receptive fields f finegrained recognition[C]2020 IEEE International Conference on Image Processing (ICIP). Abu Dhabi: IEEE, 2020: 1851 − 1855.

[22] [22] SELVARAJU R R, COGSWELL M, DAS A, et al. GradCAM: Visual explanations from deep wks via gradientbased localization[C]2017 IEEE International Conference on Computer Vision. Venice: IEEE, 2017: 618 − 626.

[23] [23] CHATTOPADHAY A, SARKAR A, HOWLADER P, et al. GradCAM++: generalized gradientbased visual explanations f deep convolutional wks[C]2018 IEEE Winter Conference on Applications of Computer Vision. Lake Tahoe: IEEE, 2018: 839 − 847.