《计算机应用》唯一官方网站 ›› 2023, Vol. 43 ›› Issue (7): 2147-2154.DOI: 10.11772/j.issn.1001-9081.2022060823
所属专题: 人工智能
收稿日期:
2022-06-08
修回日期:
2022-08-30
接受日期:
2022-09-02
发布日期:
2022-09-23
出版日期:
2023-07-10
通讯作者:
姬张建
作者简介:
姬张建(1983—),男,陕西澄城人,副教授,博士,CCF会员,主要研究方向:计算机视觉、机器学习;基金资助:
Zhangjian JI1,2(), Ming ZHANG1,2, Zilong WANG1,2
Received:
2022-06-08
Revised:
2022-08-30
Accepted:
2022-09-02
Online:
2022-09-23
Published:
2023-07-10
Contact:
Zhangjian JI
About author:
JI Zhangjian, born in 1983, Ph. D., associate professor. His research interests include computer vision, machine learning.Supported by:
摘要:
针对通用目标检测场景下,现有单阶段无锚检测器识别精度低、识别困难等问题,提出一种基于改进变焦网络VFNet(VarifocalNet)的高精度目标检测算法。首先,利用循环层聚合网络(RLANet)替换VFNet用于特征提取的主干网络ResNet,循环残差连接操作将前层特征汇入后续网络层中提升特征的表征能力;其次,通过带有特征对齐卷积操作的特征金字塔网络(FPN)替换原始的特征融合网络,利用可变形卷积操作在FPN上下层融合过程中实现特征对齐并优化特征表征能力;最后,使用聚焦-全局蒸馏(FGD)算法进一步提升小规模算法的检测性能。在COCO (Common Objects in Context) 2017数据集上进行的评估实验结果表明,在相同训练条件下,改进后的以RLANet-50为主干的算法的均值平均精度(mAP)可以达到45.9%,与VFNet算法相比提升了4.3个百分点,而改进后的算法参数量为36.67×106,与VFNet相比仅高了4×106。可见,改进后的VFNet算法在提升检测精度的同时稍微增加了参数量,说明该算法可以满足目标检测的轻量化及高精度需求。
中图分类号:
姬张建, 张明, 王子龙. 基于改进VarifocalNet的高精度目标检测算法[J]. 计算机应用, 2023, 43(7): 2147-2154.
Zhangjian JI, Ming ZHANG, Zilong WANG. High-precision object detection algorithm based on improved VarifocalNet[J]. Journal of Computer Applications, 2023, 43(7): 2147-2154.
算法 | 主干网 | 迭代次数 | mAP/% | AP50/% | AP75/% | APS/% | APM/% | APL/% |
---|---|---|---|---|---|---|---|---|
ATSS | ResNet-101 | 24 | 43.6 | 62.1 | 47.4 | 26.1 | 47.0 | 53.6 |
PAA | ResNet-101 | 24 | 44.8 | 63.3 | 48.7 | 26.5 | 48.8 | 56.3 |
GFLV1 | ResNet-101 | 24 | 45.0 | 63.7 | 48.9 | 27.2 | 48.8 | 54.5 |
IQDet | ResNet-101 | 12 | 45.1 | 63.4 | 49.3 | 26.7 | 48.5 | 56.6 |
YOLOF | ResNet-101 | 12 | 42.2 | 62.1 | 45.7 | 23.2 | 47.0 | 57.7 |
VFNet | ResNet-101 | 24 | 46.7 | 64.9 | 50.8 | 28.4 | 50.2 | 57.6 |
VFNet | ResNet-101 | 12 | 43.6 | 61.8 | 47.3 | 24.9 | 46.8 | 54.4 |
本文算法1_1x | RLANet-101 | 12 | 45.3 | 63.6 | 49.1 | 26.6 | 48.5 | 56.3 |
本文算法1_2x | RLANet-101 | 24 | 47.8 | 66.1 | 51.9 | 29.5 | 51.3 | 58.8 |
DETR | ResNet-50 | 300 | 42.1 | 63.1 | 44.5 | 19.7 | 46.3 | 60.9 |
UP-DETR | ResNet-50 | 300 | 42.8 | 63.0 | 45.3 | 20.8 | 47.1 | 61.7 |
DyHead | ResNet-50 | 12 | 43.0 | 60.7 | 46.8 | 24.7 | 46.4 | 53.9 |
GFLV1 | ResNet-50 | 24 | 43.1 | 62.0 | 46.8 | 26.0 | 46.7 | 52.3 |
VFNet | ResNet-50 | 12 | 41.6 | 59.8 | 45.0 | 23.9 | 44.6 | 51.4 |
VFNet | ResNet-50 | 24 | 44.8 | 63.1 | 48.7 | 27.2 | 48.1 | 54.8 |
本文算法2_1x | RLANet-50 | 12 | 43.1 | 61.1 | 46.7 | 25.2 | 46.0 | 53.1 |
本文算法2_2x | RLANet-50 | 24 | 45.4 | 63.4 | 49.3 | 27.7 | 48.3 | 55.7 |
本文算法3_1x | RLANet-50 | 12 | 45.9 | 63.9 | 49.8 | 26.2 | 49.6 | 57.6 |
表1 本文算法与其他先进算法在数据集COCO test-dev 2017上的性能比较
Tab. 1 Performance comparison of the proposed algorithms with other advanced algorithms on dataset COCO test-dev 2017
算法 | 主干网 | 迭代次数 | mAP/% | AP50/% | AP75/% | APS/% | APM/% | APL/% |
---|---|---|---|---|---|---|---|---|
ATSS | ResNet-101 | 24 | 43.6 | 62.1 | 47.4 | 26.1 | 47.0 | 53.6 |
PAA | ResNet-101 | 24 | 44.8 | 63.3 | 48.7 | 26.5 | 48.8 | 56.3 |
GFLV1 | ResNet-101 | 24 | 45.0 | 63.7 | 48.9 | 27.2 | 48.8 | 54.5 |
IQDet | ResNet-101 | 12 | 45.1 | 63.4 | 49.3 | 26.7 | 48.5 | 56.6 |
YOLOF | ResNet-101 | 12 | 42.2 | 62.1 | 45.7 | 23.2 | 47.0 | 57.7 |
VFNet | ResNet-101 | 24 | 46.7 | 64.9 | 50.8 | 28.4 | 50.2 | 57.6 |
VFNet | ResNet-101 | 12 | 43.6 | 61.8 | 47.3 | 24.9 | 46.8 | 54.4 |
本文算法1_1x | RLANet-101 | 12 | 45.3 | 63.6 | 49.1 | 26.6 | 48.5 | 56.3 |
本文算法1_2x | RLANet-101 | 24 | 47.8 | 66.1 | 51.9 | 29.5 | 51.3 | 58.8 |
DETR | ResNet-50 | 300 | 42.1 | 63.1 | 44.5 | 19.7 | 46.3 | 60.9 |
UP-DETR | ResNet-50 | 300 | 42.8 | 63.0 | 45.3 | 20.8 | 47.1 | 61.7 |
DyHead | ResNet-50 | 12 | 43.0 | 60.7 | 46.8 | 24.7 | 46.4 | 53.9 |
GFLV1 | ResNet-50 | 24 | 43.1 | 62.0 | 46.8 | 26.0 | 46.7 | 52.3 |
VFNet | ResNet-50 | 12 | 41.6 | 59.8 | 45.0 | 23.9 | 44.6 | 51.4 |
VFNet | ResNet-50 | 24 | 44.8 | 63.1 | 48.7 | 27.2 | 48.1 | 54.8 |
本文算法2_1x | RLANet-50 | 12 | 43.1 | 61.1 | 46.7 | 25.2 | 46.0 | 53.1 |
本文算法2_2x | RLANet-50 | 24 | 45.4 | 63.4 | 49.3 | 27.7 | 48.3 | 55.7 |
本文算法3_1x | RLANet-50 | 12 | 45.9 | 63.9 | 49.8 | 26.2 | 49.6 | 57.6 |
主干网 | 特征金字塔 | mAP | AP50 | AP75 | APS | APM | APL |
---|---|---|---|---|---|---|---|
ResNet-50 | FPN | 41.6 | 59.8 | 45.0 | 23.9 | 44.6 | 51.4 |
ResNet-50 | FPN_DCN | 41.8(+0.2) | 59.9 | 45.4 | 24.7 | 44.8 | 50.8 |
RLANet-50 | FPN | 42.9(+1.3) | 61.0 | 46.5 | 24.7 | 45.8 | 53.6 |
RLANet-50 | FPN_DCN | 43.1(+1.5) | 61.1 | 46.7 | 25.2 | 46.0 | 53.1 |
表2 检测器组件的消融实验在数据集COCO test-dev 2017上的结果 (%)
Tab. 2 Ablation experimental results of detector components on dataset COCO test-dev 2017
主干网 | 特征金字塔 | mAP | AP50 | AP75 | APS | APM | APL |
---|---|---|---|---|---|---|---|
ResNet-50 | FPN | 41.6 | 59.8 | 45.0 | 23.9 | 44.6 | 51.4 |
ResNet-50 | FPN_DCN | 41.8(+0.2) | 59.9 | 45.4 | 24.7 | 44.8 | 50.8 |
RLANet-50 | FPN | 42.9(+1.3) | 61.0 | 46.5 | 24.7 | 45.8 | 53.6 |
RLANet-50 | FPN_DCN | 43.1(+1.5) | 61.1 | 46.7 | 25.2 | 46.0 | 53.1 |
算法 | 主干网 | 特征金字塔 | 浮点计算量/GFLPOs | 参数量/106 |
---|---|---|---|---|
VFNet | ResNet-50 | FPN | 192.78 | 32.67 |
本文算法 | RLANet-50 | FPN_DCN | 212.95 | 36.67 |
表3 VFNet和本文算法的参数量和计算量比较
Tab. 3 Comparison of the number of parameters and computational cost of VFNet and the proposed algorithm
算法 | 主干网 | 特征金字塔 | 浮点计算量/GFLPOs | 参数量/106 |
---|---|---|---|---|
VFNet | ResNet-50 | FPN | 192.78 | 32.67 |
本文算法 | RLANet-50 | FPN_DCN | 212.95 | 36.67 |
算法 | mAP | AP50 | AP75 | APS | APM | APL |
---|---|---|---|---|---|---|
Student_RLANet-50 | 43.1 | 61.1 | 46.7 | 25.2 | 46.0 | 53.1 |
Teacher_RLANet-101 | 45.3 | 63.6 | 49.1 | 26.6 | 48.5 | 56.3 |
RLANet-101_FGD_RLANet-50 | 45.9 (+2.8) | 63.9 (+2.8) | 49.8 (+3.1) | 26.2 (+1.0) | 49.6 (+3.6) | 57.6 (+4.5) |
表4 使用RLANet-101对RLANet-50进行蒸馏实验 (%)
Tab. 4 Distillation experiments on RLANet-50 using RLANet-101
算法 | mAP | AP50 | AP75 | APS | APM | APL |
---|---|---|---|---|---|---|
Student_RLANet-50 | 43.1 | 61.1 | 46.7 | 25.2 | 46.0 | 53.1 |
Teacher_RLANet-101 | 45.3 | 63.6 | 49.1 | 26.6 | 48.5 | 56.3 |
RLANet-101_FGD_RLANet-50 | 45.9 (+2.8) | 63.9 (+2.8) | 49.8 (+3.1) | 26.2 (+1.0) | 49.6 (+3.6) | 57.6 (+4.5) |
算法 | 主干网 | 特征金字塔网络 | 浮点计算量/GFLOPs | 参数量/106 |
---|---|---|---|---|
Student_RLANet-50 | RLANet-50 | FPN_DCN | 192.78 | 32.67 |
Teacher_RLANet-101 | RLANet-101 | FPN_DCN | 292.51 | 55.81 |
RLANet-101_FGD_RLANet-50 | RLANet-50 | FPN_DCN | 192.78 | 32.67 |
表5 蒸馏操作前后的参数量和计算量比较
Tab. 5 Comparison of the number of parameters and computational cost before and after distillation operation
算法 | 主干网 | 特征金字塔网络 | 浮点计算量/GFLOPs | 参数量/106 |
---|---|---|---|---|
Student_RLANet-50 | RLANet-50 | FPN_DCN | 192.78 | 32.67 |
Teacher_RLANet-101 | RLANet-101 | FPN_DCN | 292.51 | 55.81 |
RLANet-101_FGD_RLANet-50 | RLANet-50 | FPN_DCN | 192.78 | 32.67 |
1 | 张慧,王坤峰,王飞跃.深度学习在目标视觉检测中的应用进展与展望[J].自动化学报, 2017, 43(8): 1289-1305. 10.16383/j.aas.2017.c160822 |
ZHANG H, WANG K F, WANG F Y. Advances and perspectives on applications of deep learning in visual object detection[J]. Acta Automatica Sinica, 2017, 43(8): 1289-1305. 10.16383/j.aas.2017.c160822 | |
2 | JIAO L C, ZHANG F, LIU F, et al. A survey of deep learning-based object detection[J]. IEEE Access, 2019, 7: 128837-128868. 10.1109/access.2019.2939201 |
3 | 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 |
4 | ZHANG H Y, WANG Y, DAYOUB F, et al. VarifocalNet: an IoU-aware dense object detector [C]// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 8514-8523. 10.1109/cvpr46437.2021.00841 |
5 | 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 |
6 | ZHAO J Y, FANG Y W, LI G D. Recurrence along depth: deep convolutional neural networks with recurrent layer aggregation[C/OL]// Proceedings of the 35th Conference on Neural Information Processing Systems [2022-02-20]. . |
7 | DAI J F, QI H Z, XIONG Y W, et al. Deformable convolutional networks [C]// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 764-773. 10.1109/iccv.2017.89 |
8 | ZHU X Z, HU H, LIN S, et al. Deformable ConvNets v2: more deformable, better results [C]// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 9300-9308. 10.1109/cvpr.2019.00953 |
9 | YANG Z D, LI Z, JIANG X H, et al. Focal and global knowledge distillation for detectors [C]// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 4633-4642. 10.1109/cvpr52688.2022.00460 |
10 | LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: common objects in context [C]// Proceedings of the 2014 European Conference on Computer Vision, LNCS 8693. Cham: Springer, 2014: 740-755. |
11 | 罗会兰,陈鸿坤.基于深度学习的目标检测研究综述[J].电子学报, 2020, 48(6): 1230-1239. 10.3969/j.issn.0372-2112.2020.06.026 |
LUO H L, CHEN H K. Survey of object detection based on deep learning[J]. Acta Electronica Sinica, 2020, 48(6): 1230-1239. 10.3969/j.issn.0372-2112.2020.06.026 | |
12 | 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 |
13 | REDMON J, FARHADI A. YOLO9000: better, faster, stronger [C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 6517-6525. 10.1109/cvpr.2017.690 |
14 | REDMON J, FARHADI A. YOLOv3: an incremental improvement[EB/OL]. (2018-04-08) [2022-02-20]. . 10.1109/cvpr.2017.690 |
15 | BOCHKOVSKIY A, WANG C Y, LIAO H Y M. A.YOLOv4: optimal speed and accuracy of object detection [EB/OL]. (2020-04-23) [2022-02-20]. . |
16 | 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. |
17 | LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection [C]// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 2999-3007. 10.1109/iccv.2017.324 |
18 | 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 |
19 | 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 |
20 | CAI Z W, VASCONCELOS N. Cascade R-CNN: delving into high quality object detection [C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 6154-6162. 10.1109/cvpr.2018.00644 |
21 | ZHOU X Y, WANG D Q, KRÄHENBÜHL P. Objects as points[EB/OL]. (2019-04-25) [2022-02-20]. . 10.5260/chara.21.2.8 |
22 | YANG Z, LIU S H, HU H, et al. RepPoints: point set representation for object detection [C]// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2019: 9656-9665. 10.1109/iccv.2019.00975 |
23 | TIAN Z, SHEN C H, CHEN H, et al. FCOS: fully convolutional one-stage object detection [C]// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2019: 9627-9636. 10.1109/iccv.2019.00972 |
24 | HUANG G, LIU Z, L van der MAATEN, et al. Densely connected convolutional networks [C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 2261-2269. 10.1109/cvpr.2017.243 |
25 | HU J, SHEN L, SUN G. Squeeze-and-excitation networks [C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 7132-7141. 10.1109/cvpr.2018.00745 |
26 | WANG Q L, WU B G, ZHU P F, et al. ECA-Net: efficient channel attention for deep convolutional neural networks [C]// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 11531-11539. 10.1109/cvpr42600.2020.01155 |
27 | LIU S, QI L, QIN H F, et al. Path aggregation network for instance segmentation [C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 8759-8768. 10.1109/cvpr.2018.00913 |
28 | TAN M X, PANG R M, LE Q V. EfficientDet: scalable and efficient object detection [C]// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 10778-10787. 10.1109/cvpr42600.2020.01079 |
29 | CHEN G B, CHOI W, YU X, et al. Learning efficient object detection models with knowledge distillation [C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc., 2017: 742-751. |
30 | LI Q Q, JIN S Y, YAN J J. Mimicking very efficient network for object detection [C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 7341-7349. 10.1109/cvpr.2017.776 |
31 | WANG T, YUAN L, ZHANG X P, et al. Distilling object detectors with fine-grained feature imitation [C]// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 4928-4937. 10.1109/cvpr.2019.00507 |
32 | REZATOFIGHI H, TSOI N, GWAK J, et al. Generalized intersection over union: a metric and a loss for bounding box regression [C]// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 658-666. 10.1109/cvpr.2019.00075 |
33 | ZHANG S F, CHI C, YAO Y Q, et al. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection [C]// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 9756-9765. 10.1109/cvpr42600.2020.00978 |
34 | KIM K, LEE H S. Probabilistic anchor assignment with IoU prediction for object detection [C]// Proceedings of the 2020 European Conference on Computer Vision, LNCS 12370. Cham: Springer, 2020: 355-371. |
35 | LI X, WANG W H, WU L J, et al. Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection [C]// Proceedings of the 34th International Conference on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc., 2020: 21002-21012. |
36 | MA Y C, LIU S T, LI Z M, et al. IQDet: instance-wise quality distribution sampling for object detection [C]// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 1717-1725. 10.1109/cvpr46437.2021.00176 |
37 | CHEN Q, WANG Y M, YANG T, et al. You only look one-level feature [C]// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 13034-13043. 10.1109/cvpr46437.2021.01284 |
38 | CARION N, MASSA F, SYNNAEVE G, et al. End-to-end object detection with transformers [C]// Proceedings of the 2020 European Conference on Computer Vision, LNCS 12346. Cham: Springer, 2020: 213-229. |
39 | DAI Z G, CAI B L, LIN Y G, et al. UP-DETR: unsupervised pre-training for object detection with transformers [C]// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 1601-1610. 10.1109/cvpr46437.2021.00165 |
40 | DAI X Y, CHEN Y P, XIAO B, et al. Dynamic head: unifying object detection heads with attentions [C]// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 7369-7378. 10.1109/cvpr46437.2021.00729 |
[1] | 贾洁茹, 杨建超, 张硕蕊, 闫涛, 陈斌. 基于自蒸馏视觉Transformer的无监督行人重识别[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2893-2902. |
[2] | 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. |
[3] | 李烨恒, 罗光圣, 苏前敏. 基于改进YOLOv5的Logo检测算法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2580-2587. |
[4] | 赵宇博, 张丽萍, 闫盛, 侯敏, 高茂. 基于改进分段卷积神经网络和知识蒸馏的学科知识实体间关系抽取[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2421-2429. |
[5] | 张英俊, 李牛牛, 谢斌红, 张睿, 陆望东. 课程学习指导下的半监督目标检测框架[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2326-2333. |
[6] | 徐松, 张文博, 王一帆. 基于时空信息的轻量视频显著性目标检测网络[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2192-2199. |
[7] | 孙逊, 冯睿锋, 陈彦如. 基于深度与实例分割融合的单目3D目标检测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2208-2215. |
[8] | 姬张建, 杜娜. 基于改进VariFocalNet的微小目标检测[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2200-2207. |
[9] | 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. |
[10] | 邓亚平, 李迎江. YOLO算法及其在自动驾驶场景中目标检测综述[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1949-1958. |
[11] | 耿焕同, 刘振宇, 蒋骏, 范子辰, 李嘉兴. 基于改进YOLOv8的嵌入式道路裂缝检测算法[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1613-1618. |
[12] | 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. |
[13] | 宋霄罡, 张冬冬, 张鹏飞, 梁莉, 黑新宏. 面向复杂施工环境的实时目标检测算法[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1605-1612. |
[14] | 陈天华, 朱家煊, 印杰. 基于注意力机制的鸟类识别算法[J]. 《计算机应用》唯一官方网站, 2024, 44(4): 1114-1120. |
[15] | 李雨秋, 侯利萍, 薛健, 吕科, 王泳. 基于内容解译的遥感图像推荐方法[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 722-731. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||