[3] [3] HENDRYCKS D,DIETTERICH T.Benchmarking neural ne- twork robustness to common corruptions and perturbations［EB/OL］.(2019-03-28)［2022-07-28］.https://arxiv.org/abs/1903.12261.

[4] [4] HENDRYCKS D,MU N,CUBUK E D,et al.Augmix: a simple data processing method to improve robustness and uncertainty［EB/OL］.(2020-02-17)［2022-07-28］.https://arxiv.org/abs/1912.02781v2.

[5] [5] CHEN M,WANG Z,ZHENG F.Benchmarks for corruption invariant person re-identification［EB/OL］. (2021-11-01)［2022-07-28］.https://arxiv.org/abs/2111.00880v1.

[6] [6] BISWAS K,KUMAR S,BANERJEE S,et al.SMU:Smooth activation function for deep networks using smoothing maximum technique［EB/OL］. (2022-04-11)［2022-07-28］.https://arxiv.org/abs/2111.04682v2.

[7] [7] PRAJIT R, BARRET Z, QUOC V. Searching for activation functions［EB/OL］. (2017-10-16)［2022-07-28］. https://arxiv.org/abs/1710.05941v2.

[8] [8] WANG F,JIANG M,QIAN C,et al.Residual attention network for image classification［C］//IEEE Conference on Computer Vision and Pattern Recognition,July 21-26,2018,Honolulu,HI,USA.New York:IEEE,2017:3156-3164.

[9] [9] WOO S,PARK J,LEE J Y,et al.CBAM:convolutional block attention module［C］//European Conference on Computer Vision,September 8-14,2018,Munich,Germany.Berlin:Springer,2018:3-19.

[10] [10] JIN X,LAN C,ZENG W,et al.Style normalization and restitution for generalizable person re-identification［C］//IEEE/CVF Conference on Computer Vision and Pattern Recognition,September 13-19,2020,Seattle,WA,USA.New York:IEEE,2020:3143-3152.

[11] [11] LIU Y,SHAO Z,HOFFMANN N.Global attention mechanism: retain information to enhance channel-spatial interactions［EB/OL］.(2021-12-10)［2022-07-28］.https://arxiv.org/abs/2112.05561.

[12] [12] ZHOU K,YANG Y,CAVALLARO A,et al.Omni-scale feature learning for person re-identification［C］//IEEE/CVF International Conference on Computer Vision,June 15-20,2019,Long Beach,CA,USA.New York:IEEE,2019:3702-3712.

[13] [13] HUANG X,BELONGIE S.Arbitrary style transfer in real-time with adaptive instance normalization［C］//IEEE International Conference on Computer Vision,October 22-29,2017,Venice,Italy.New York:IEEE,2017:1501-1510.

[14] [14] PAN X,LUO P,SHI J,et al.Two at once: enhang learning and generalization capacities via IBN-Net［C］//European Conference on Computer Vision,September 8-14,2018,Munich,Germany.Berlin:Springer,2018:464-479.

[15] [15] HU J,SHEN L,SUN G.Squeeze-and-excitation networks［C］//IEEE Conference on Computer Vision and Pattern Recognition,June 18-23,2018,Salt Lake City,UT,USA.New York:IEEE,2018:7132-7141.

[16] [16] ZHENG Z,ZHENG L,YANG Y.A discriminatively learned CNN embedding for person re-identification［EB/OL］.(2017-02-03)［2022-07-28］.https://arxiv.org/abs/1611.05666.

[17] [17] HERMANS A,BEYERL,LEIBE B.In defense of the triplet loss for person re-identification［EB/OL］. (2017-03-22)［2022-07-28］.https://arxiv.org/abs/1703.07737.

[18] [18] LUO H,GU Y,LIAO X,et al.Bag of tricks and a strong baseline for deep person re-identification［C］//IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops,June 15-20,2019,Long Beach,CA,USA.New York:IEEE,2019:8514-8522.

[19] [19] YE M,SHEN J,LIN G,et al.Deep learning for person re-identification:a survey and outlook[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2021,44(6): 2872-2893.