《计算机应用》唯一官方网站 ›› 2023, Vol. 43 ›› Issue (8): 2602-2610.DOI: 10.11772/j.issn.1001-9081.2022071009
所属专题: 多媒体计算与计算机仿真
收稿日期:
2022-07-11
修回日期:
2022-11-18
接受日期:
2022-11-30
发布日期:
2023-01-15
出版日期:
2023-08-10
通讯作者:
吴亮红
作者简介:
刘欢(1997—),女,河南南阳人,硕士研究生,CCF会员,主要研究方向:图像处理基金资助:
Huan LIU, Lianghong WU(), Lyu ZHANG, Liang CHEN, Bowen ZHOU, Hongqiang ZHANG
Received:
2022-07-11
Revised:
2022-11-18
Accepted:
2022-11-30
Online:
2023-01-15
Published:
2023-08-10
Contact:
Lianghong WU
About author:
LIU Huan, born in 1997, M. S. candidate. Her research interests include image processing.Supported by:
摘要:
针对实际检测过程中复杂场景下由白细胞的形态、染色程度差异较大而导致白细胞检测困难的问题,提出一种基于特征双融合CenterNet的白细胞检测方法TFF-CenterNet(Twice-Fusion-Feature CenterNet)。首先,通过特征金字塔网络(FPN)将主干网络特征与反卷积层特征相融合,增强方法的特征提取能力,从而解决白细胞个体差异、染色程度不同等问题;然后,针对白细胞占据图像面积与图像背景面积严重不均衡的问题,改进热力图损失函数来提升对白细胞正样本的关注以提高检测平均精度均值(mAP);最后,针对白细胞图像目标微小、位置随机、细胞粘连的特点,引入坐标注意力和坐标卷积,提高对白细胞位置信息的关注度和敏感性。对于复杂场景下的白细胞,TFF-CenterNet的mAP达到97.01%,比CenterNet高3.24个百分点;检测速度达到167 frame/s,比CenterNet快42 frame/s。实验结果表明,所提方法在复杂情况下能在提高白细胞检测mAP的同时达到实时性要求,并提升了鲁棒性,可为辅助医疗诊断中白细胞的快速自动检测提供技术支持。
中图分类号:
刘欢, 吴亮红, 张侣, 陈亮, 周博文, 张红强. 基于特征双融合CenterNet的白细胞检测方法[J]. 计算机应用, 2023, 43(8): 2602-2610.
Huan LIU, Lianghong WU, Lyu ZHANG, Liang CHEN, Bowen ZHOU, Hongqiang ZHANG. Leukocyte detection method based on twice-fusion-feature CenterNet[J]. Journal of Computer Applications, 2023, 43(8): 2602-2610.
数据集 | 训练样本数 | 验证样本数 | 测试样本数 | 总计样本数 |
---|---|---|---|---|
BCCD | 204 | 51 | 109 | 364 |
BCSI100 | 617 | 154 | 331 | 1 002 |
BCSI40 | 1 851 | 463 | 991 | 3 305 |
表1 数据集样本数
Tab. 1 Numbers of samples in datasets
数据集 | 训练样本数 | 验证样本数 | 测试样本数 | 总计样本数 |
---|---|---|---|---|
BCCD | 204 | 51 | 109 | 364 |
BCSI100 | 617 | 154 | 331 | 1 002 |
BCSI40 | 1 851 | 463 | 991 | 3 305 |
主干网络 | mAP(IoU=0.5)/% | F1 | 检测 速度/(frame·s-1) | 权重所占内存/MB |
---|---|---|---|---|
ResNet18 | 91.36 | 0.90 | 192 | 54 |
ResNet34 | 93.69 | 0.92 | 167 | 92 |
ResNet50 | 93.77 | 0.92 | 125 | 125 |
表2 主干特征提取网络对比实验
Tab. 2 Comparison experiment of backbone feature extraction network
主干网络 | mAP(IoU=0.5)/% | F1 | 检测 速度/(frame·s-1) | 权重所占内存/MB |
---|---|---|---|---|
ResNet18 | 91.36 | 0.90 | 192 | 54 |
ResNet34 | 93.69 | 0.92 | 167 | 92 |
ResNet50 | 93.77 | 0.92 | 125 | 125 |
P/% | R/% | mAP(IoU=0.5)/% | F1 | |
---|---|---|---|---|
0.6 | 97.34 | 83.26 | 90.35 | 0.90 |
0.7 | 95.78 | 92.88 | 93.78 | 0.94 |
0.8 | 93.15 | 94.11 | 94.72 | 0.94 |
0.9 | 95.15 | 92.81 | 94.02 | 0.94 |
— | 97.89 | 84.73 | 93.25 | 0.92 |
表3 λ取值对比实验
Tab. 3 Comparison experiment of λ value
P/% | R/% | mAP(IoU=0.5)/% | F1 | |
---|---|---|---|---|
0.6 | 97.34 | 83.26 | 90.35 | 0.90 |
0.7 | 95.78 | 92.88 | 93.78 | 0.94 |
0.8 | 93.15 | 94.11 | 94.72 | 0.94 |
0.9 | 95.15 | 92.81 | 94.02 | 0.94 |
— | 97.89 | 84.73 | 93.25 | 0.92 |
改进点1 | 改进点2 | 改进点3 | P/% | R/% | mAP(IoU=0.5)/% | F1 |
---|---|---|---|---|---|---|
× | × | × | 96.55 | 84.73 | 93.25 | 0.92 |
√ | × | × | 95.23 | 92.72 | 94.55 | 0.93 |
× | √ | × | 93.15 | 94.11 | 94.72 | 0.94 |
× | × | √ | 94.60 | 91.45 | 94.00 | 0.93 |
√ | √ | × | 95.75 | 95.75 | 96.04 | 0.96 |
√ | × | √ | 95.20 | 93.73 | 95.03 | 0.94 |
× | √ | √ | 95.37 | 94.05 | 95.38 | 0.95 |
√ | √ | √ | 96.75 | 96.97 | 97.01 | 0.96 |
表4 消融实验
Tab. 4 Ablation experiments
改进点1 | 改进点2 | 改进点3 | P/% | R/% | mAP(IoU=0.5)/% | F1 |
---|---|---|---|---|---|---|
× | × | × | 96.55 | 84.73 | 93.25 | 0.92 |
√ | × | × | 95.23 | 92.72 | 94.55 | 0.93 |
× | √ | × | 93.15 | 94.11 | 94.72 | 0.94 |
× | × | √ | 94.60 | 91.45 | 94.00 | 0.93 |
√ | √ | × | 95.75 | 95.75 | 96.04 | 0.96 |
√ | × | √ | 95.20 | 93.73 | 95.03 | 0.94 |
× | √ | √ | 95.37 | 94.05 | 95.38 | 0.95 |
√ | √ | √ | 96.75 | 96.97 | 97.01 | 0.96 |
数据集 | P/% | R/% | mAP(IoU=0.5)/% | F1 |
---|---|---|---|---|
BCCD | 98.70 | 98.26 | 98.98 | 0.98 |
BCSI100 | 96.37 | 96.22 | 97.19 | 0.96 |
BCSI40 | 95.75 | 96.97 | 97.01 | 0.96 |
表5 不同数据集上的对比实验
Tab. 5 Comparison experiments on different datasets
数据集 | P/% | R/% | mAP(IoU=0.5)/% | F1 |
---|---|---|---|---|
BCCD | 98.70 | 98.26 | 98.98 | 0.98 |
BCSI100 | 96.37 | 96.22 | 97.19 | 0.96 |
BCSI40 | 95.75 | 96.97 | 97.01 | 0.96 |
方法 | P% | R% | mAP(IoU=0.5)/% | F1 | 检测速度 /(frame·s-1) | 权重所占内存/MB | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
BCCD | BCSI100 | BCSI40 | BCCD | BCSI100 | BCSI40 | BCCD | BCSI100 | BCSI40 | BCCD | BCSI100 | BCSI40 | |||
Faster RCNN[ | 98.12 | 57.89 | 54.57 | 81.59 | 79.34 | 78.50 | 89.67 | 72.16 | 68.80 | 0.89 | 0.71 | 0.64 | 18 | 108 |
SSD(VGG16)[ | 96.34 | 83.75 | 70.34 | 82.53 | 83.24 | 82.42 | 87.35 | 84.29 | 76.77 | 0.87 | 0.85 | 0.78 | 28 | 100 |
YOLOv4 (DarkNet53)[ | 98.37 | 95.88 | 95.24 | 94.95 | 94.75 | 94.24 | 96.57 | 95.34 | 95.10 | 0.96 | 0.96 | 0.95 | 40 | 245 |
YOLOv5s[ | 97.53 | 96.13 | 95.58 | 93.45 | 95.47 | 94.16 | 97.13 | 95.89 | 95.31 | 0.96 | 0.96 | 0.95 | 55 | 140 |
RetinaNet (ResNet50)[ | 98.44 | 96.54 | 96.25 | 92.59 | 93.39 | 85.87 | 97.32 | 95.39 | 94.89 | 0.96 | 0.95 | 0.91 | 36 | 139 |
CenterNet (ResNet50)[ | 97.56 | 96.47 | 95.84 | 89.23 | 92.34 | 89.47 | 95.44 | 94.79 | 93.77 | 0.95 | 0.94 | 0.92 | 125 | 125 |
CenterNet (Hourglass104)[ | 98.34 | 98.16 | 95.99 | 90.32 | 96.45 | 98.69 | 98.01 | 97.56 | 97.36 | 0.97 | 0.96 | 0.96 | 20 | 730 |
TFF-CenterNet (ResNet34) | 98.70 | 96.37 | 96.75 | 98.26 | 96.22 | 96.97 | 98.98 | 97.19 | 97.01 | 0.98 | 0.96 | 0.96 | 167 | 92 |
表6 不同方法的白细胞检测结果对比
Tab. 6 Comparison of leukocyte detection results of different methods
方法 | P% | R% | mAP(IoU=0.5)/% | F1 | 检测速度 /(frame·s-1) | 权重所占内存/MB | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
BCCD | BCSI100 | BCSI40 | BCCD | BCSI100 | BCSI40 | BCCD | BCSI100 | BCSI40 | BCCD | BCSI100 | BCSI40 | |||
Faster RCNN[ | 98.12 | 57.89 | 54.57 | 81.59 | 79.34 | 78.50 | 89.67 | 72.16 | 68.80 | 0.89 | 0.71 | 0.64 | 18 | 108 |
SSD(VGG16)[ | 96.34 | 83.75 | 70.34 | 82.53 | 83.24 | 82.42 | 87.35 | 84.29 | 76.77 | 0.87 | 0.85 | 0.78 | 28 | 100 |
YOLOv4 (DarkNet53)[ | 98.37 | 95.88 | 95.24 | 94.95 | 94.75 | 94.24 | 96.57 | 95.34 | 95.10 | 0.96 | 0.96 | 0.95 | 40 | 245 |
YOLOv5s[ | 97.53 | 96.13 | 95.58 | 93.45 | 95.47 | 94.16 | 97.13 | 95.89 | 95.31 | 0.96 | 0.96 | 0.95 | 55 | 140 |
RetinaNet (ResNet50)[ | 98.44 | 96.54 | 96.25 | 92.59 | 93.39 | 85.87 | 97.32 | 95.39 | 94.89 | 0.96 | 0.95 | 0.91 | 36 | 139 |
CenterNet (ResNet50)[ | 97.56 | 96.47 | 95.84 | 89.23 | 92.34 | 89.47 | 95.44 | 94.79 | 93.77 | 0.95 | 0.94 | 0.92 | 125 | 125 |
CenterNet (Hourglass104)[ | 98.34 | 98.16 | 95.99 | 90.32 | 96.45 | 98.69 | 98.01 | 97.56 | 97.36 | 0.97 | 0.96 | 0.96 | 20 | 730 |
TFF-CenterNet (ResNet34) | 98.70 | 96.37 | 96.75 | 98.26 | 96.22 | 96.97 | 98.98 | 97.19 | 97.01 | 0.98 | 0.96 | 0.96 | 167 | 92 |
1 | CAO H C, LIU H, SONG E M. A novel algorithm for segmentation of leukocytes in peripheral blood[J]. Biomedical Signal Processing and Control, 2018, 45:10-21. 10.1016/j.bspc.2018.05.010 |
2 | 孙凯,姚旭峰,马风玲,等. 基于机器学习的血细胞分类研究进展[J]. 中国医学物理学杂志, 2020, 37(1):127-132. 10.3969/j.issn.1005-202X.2020.01.023 |
SUN K, YAO X F, MA F L, et al. Blood cell classification based on machine learning[J]. Chinese Journal of Medical Physics, 2020, 37(1):127-132. 10.3969/j.issn.1005-202X.2020.01.023 | |
3 | SAJJAD M, KHAN S, SHOAIB M, et al. Computer aided system for leukocytes classification and segmentation in blood smear images[C]// Proceedings of 2016 International Conference on Frontiers of Information Technology. Piscataway: IEEE, 2016:99-104. 10.1109/fit.2016.026 |
4 | DUAN Y F, WANG J S, HU M H, et al. Leukocyte classification based on spatial and spectral features of microscopic hyperspectral images[J]. Optics and Laser Technology, 2019, 112: 530-538. 10.1016/j.optlastec.2018.11.057 |
5 | NAZLIBILEK S, KARACOR D, ERCAN T, et al. Automatic segmentation, counting, size determination and classification of white blood cells[J]. Measurement, 2014, 55:58-65. 10.1016/j.measurement.2014.04.008 |
6 | SU M C, CHENG C Y, WANG P C. A neural-network-based approach to white blood cell classification[J]. The Scientific World Journal, 2014, 2014: No.796371. 10.1155/2014/796371 |
7 | 周飞燕,金林鹏,董军. 卷积神经网络研究综述[J]. 计算机学报, 2017, 40(6): 1229-1251. 10.11897/SP.J.1016.2017.01229 |
ZHOU F Y, JIN L P, DONG J. Review of convolutional neural network[J]. Chinese Journal of Computers, 2017, 40(6): 1229-1251. 10.11897/SP.J.1016.2017.01229 | |
8 | KUTLU H, AVCI E, ÖZYURT F. White blood cells detection and classification based on regional convolutional neural networks[J]. Medical Hypotheses, 2020, 135: No.109472. 10.1016/j.mehy.2019.109472 |
9 | ZHAO J W, ZHANG M S, ZHOU Z H, et al. Automatic detection and classification of leukocytes using convolutional neural networks[J]. Medical and Biological Engineering and Computing, 2017, 55(8):1287-1301. 10.1007/s11517-016-1590-x |
10 | NATEGHI R, FATEHI M, SADEGHITABAR A, et al. Automatic detection and classification of white blood cells in blood smear images using convolutional neural network[J]. Iranian Journal of Radiology, 2019, 16(Special Issue): No.e99159. 10.5812/iranjradiol.99159 |
11 | FAN H Y, ZHANG F B, XI L, et al. LeukocyteMask: an automated localization and segmentation method for leukocyte in blood smear images using deep neural networks[J]. Journal of Biophotonics, 2019, 12(7): No.e201800488. 10.1002/jbio.201800488 |
12 | 刘阳. 基于卷积神经网络和胶囊网络的白细胞图像分类技术研究[D]. 包头:内蒙古科技大学, 2020:19-34. |
LIU Y. Image classification of white blood cells based on convolutional neural network and capsule network[D]. Baotou: Inner Mongolia University of Science and Technology, 2020:19-34. | |
13 | LU Y, QIN X J, FAN H Y, et al. WBC-Net: a white blood cell segmentation network based on UNet++ and ResNet[J]. Applied Soft Computing, 2021, 101: No.107006. 10.1016/j.asoc.2020.107006 |
14 | WANG Q W, BI S S, SUN M L, et al. Deep learning approach to peripheral leukocyte recognition[J]. PLoS ONE, 2019, 4(6): No.e0218808. 10.1371/journal.pone.0218808 |
15 | 耿磊,杨盟盟,肖志涛,等. 结合通道空间加权特征金字塔网络的白细胞检测与分割[J]. 计算机辅助设计与图形学学报, 2021, 33(9):1418-1427. 10.3724/sp.j.1089.2021.18672 |
GENG L, YANG M M, XIAO Z T, et al. White blood cell detection and segmentation combined with the channel space weighted feature pyramid networks[J]. Journal of Computer-Aided Design and Computer Graphics, 2021, 33(9): 1418-1427. 10.3724/sp.j.1089.2021.18672 | |
16 | 陈奕君. 基于半监督学习的外周血白细胞自动分类识别[D]. 南京:东南大学, 2021: 16-31. |
CHEN Y J. Automatic classification and recognition of peripheral blood leukocytes based on semi-supervised learning[D]. Nanjing: Southeast University, 2021:16-31. | |
17 | 王榆锋,李大海. 改进YOLO框架的血细胞检测算法[J]. 计算机工程与应用, 2022, 58(12):191-198. 10.3778/j.issn.1002-8331.2110-0224 |
WANG Y F, LI D H. Improved YOLO framework blood cell detection algorithm[J]. Computer Engineering and Applications, 2022, 58(12):191-198. 10.3778/j.issn.1002-8331.2110-0224 | |
18 | MOHAMED M, FAR B, GUAILY A. An efficient technique for white blood cells nuclei automatic segmentation[C]// Proceedings of the 2012 IEEE International Conference on Systems, Man, and Cybernetics. Piscataway: IEEE, 2012:220-225. 10.1109/icsmc.2012.6377703 |
19 | 王静,孙紫雲,郭苹,等. 改进YOLOv5的白细胞检测算法[J]. 计算机工程与应用, 2022, 58(4):134-142. 10.3778/j.issn.1002-8331.2107-0332 |
WANG J, SUN Z Y, GUO P, et al. Improved leukocyte detection algorithm of YOLOv5[J]. Computer Engineering and Applications, 2022, 58(4):134-142. 10.3778/j.issn.1002-8331.2107-0332 | |
20 | 姚江帆. 基于深度学习目标检测的白细胞分类技术研究[D]. 杭州:杭州电子科技大学, 2022: 19-35. |
YAO J F. Research on leukocyte classification technology based on deep learning with object detection[D]. Hangzhou: Hangzhou Dianzi University, 2022: 19-35. | |
21 | ZHOU X Y, WANG D Q, KRÄHENBÜHL P. Objects as points[EB/OL]. (2019-04-25) [2021-10-22].. 10.5260/chara.21.2.8 |
22 | GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]// Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2014:580-587. 10.1109/cvpr.2014.81 |
23 | GIRSHICK R. Fast R-CNN[C]// Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2015: 1440-1448. 10.1109/iccv.2015.169 |
24 | REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1137-1149. 10.1109/tpami.2016.2577031 |
25 | REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 779-788. 10.1109/cvpr.2016.91 |
26 | BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection[EB/OL]. (2020-04-23) [2021-11-12]. |
27 | Ultralytics. YOLOv5[CP/OL]. [2021-11-26].. 10.1117/1.jei.31.3.033033 |
28 | LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multiBox detector[C]// Proceedings of the 2016 European Conference on Computer Vision, LNCS 9905. Cham: Springer, 2016:21-37. |
29 | LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(2): 318-327. 10.1109/tpami.2018.2858826 |
30 | NEWELL A, YANG K Y, DENG J. Stacked hourglass networks for human pose estimation[C]// Proceedings of the 2016 European Conference on Computer Vision, LNCS 9912. Cham: Springer, 2016:483-499. |
31 | YU F, WANG D Q, SHELHAMER E, et al. Deep layer aggregation[C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 2403-2412. 10.1109/cvpr.2018.00255 |
32 | HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 770-778. 10.1109/cvpr.2016.90 |
33 | HOU Q B, ZHOU D Q, FENG J S. Coordinate attention for efficient mobile network design[C]// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 13708-13717. 10.1109/cvpr46437.2021.01350 |
34 | LIN T Y, DOLLÁR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 936-944. 10.1109/cvpr.2017.106 |
35 | CHEN L C, PAPANDREOU G, KOKKINOS I, et al. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4): 834-848. 10.1109/tpami.2017.2699184 |
36 | 赵斐. 基于金字塔注意力机制的遥感图像语义分割[J]. 国外电子测量技术, 2019, 38(8):150-154. |
ZHAO F. Semantic segmentation of remote sensing images based on pyramid attention mechanism[J]. Foreign Electronic Measurement Technology, 2019, 38(8):150-154. | |
37 | HU J, SHEN L, ALBANIE S, et al. Squeeze-and-excitation networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(8): 2011-2023. 10.1109/tpami.2019.2913372 |
38 | LIU R, LEHMAN J, MOLINO P, et al. An intriguing failing of convolutional neural networks and the CoordConv solution[C]// Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc., 2018:9628-9639. 10.1109/icinpro43533.2018.9096860 |
39 | 张福玲,张少敏,支力佳,等. 融合注意力机制和特征金字塔网络的CT图像肺结节检测[J]. 中国图象图形学报, 2021, 26(9):2156-2170. 10.11834/jig.210160 |
ZHANG F L, ZHANG S M, ZHI L J, et al. Detection of pulmonary nodules in CT images by combining an attention mechanism and a feature pyramid network[J]. Journal of Image and Graphics, 2021, 26(9):2156-2170. 10.11834/jig.210160 | |
40 | 徐晓光,李海. 多尺度特征在YOLO算法中的应用研究[J]. 电子测量与仪器学报, 2021, 35(6): 96-101. |
XU X G, LI H. Application research of multi-scale features in YOLO algorithm[J]. Journal of Electronic Measurement and Instrumentation, 2021, 35(6):96-101. | |
41 | 化嫣然,张卓,龙赛,等. 基于改进YOLO算法的遥感图像目标检测[J]. 电子测量技术, 2020, 43(24): 87-92. |
HUA Y R, ZHANG Z, LONG S, et al. Remote sensing image target detection based on improved YOLO algorithm[J]. Electronic Measurement Technology, 2020, 43(24):87-92. | |
42 | 蓝金辉,王迪,申小盼. 卷积神经网络在视觉图像检测的研究进展[J].仪器仪表学报, 2020, 41(4): 167-182. 10.19650/j.cnki.cjsi.J2006003 |
LAN J H, WANG D, SHEN X P. Research progress on visual image detection based on convolutional neural network[J]. Chinese Journal of Scientific Instrument, 2020, 41(4):167-182. 10.19650/j.cnki.cjsi.J2006003 |
[1] | 潘烨新, 杨哲. 基于多级特征双向融合的小目标检测优化模型[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2871-2877. |
[2] | 高鹏淇, 黄鹤鸣, 樊永红. 融合坐标与多头注意力机制的交互语音情感识别[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2400-2406. |
[3] | 刘瑞华, 郝子赫, 邹洋杨. 基于多层级精细特征融合的步态识别算法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2250-2257. |
[4] | 黄梦源, 常侃, 凌铭阳, 韦新杰, 覃团发. 基于层间引导的低光照图像渐进增强算法[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1911-1919. |
[5] | 程小辉, 黄云天, 张瑞芳. 基于多尺度和加权坐标注意力的轻量化红外道路场景检测模型[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1927-1934. |
[6] | 刘越, 刘芳, 武奥运, 柴秋月, 王天笑. 基于自注意力机制与图卷积的3D目标检测网络[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1972-1977. |
[7] | 李鸿天, 史鑫昊, 潘卫国, 徐成, 徐冰心, 袁家政. 融合多尺度和注意力机制的小样本目标检测[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1437-1444. |
[8] | 李鑫, 孟乔, 皇甫俊逸, 孟令辰. 基于分离式标签协同学习的YOLOv5多属性分类[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1619-1628. |
[9] | 韩贵金, 张馨渊, 张文涛, 黄娅. 基于多特征融合的自监督图像配准算法[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1597-1604. |
[10] | 李新叶, 侯晔凝, 孔英会, 燕志旗. 结合特征融合与增强注意力的少样本目标检测[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 745-751. |
[11] | 吴宁, 罗杨洋, 许华杰. 基于多尺度特征融合的遥感图像语义分割方法[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 737-744. |
[12] | 郑宇亮, 陈云华, 白伟杰, 陈平华. 融合事件数据和图像帧的车辆目标检测[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 931-937. |
[13] | 蒋占军, 吴佰靖, 马龙, 廉敬. 多尺度特征和极化自注意力的Faster-RCNN水漂垃圾识别[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 938-944. |
[14] | 贾宗泽, 高鹏飞, 马应龙, 刘晓峰, 夏海鑫. 基于注意力机制的多特征融合对话行为层次化分类方法[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 715-721. |
[15] | 黄子麒, 胡建鹏. 实体类别增强的汽车领域嵌套命名实体识别[J]. 《计算机应用》唯一官方网站, 2024, 44(2): 377-384. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||