Domain Adaptive Multi-Discriminator Object Detection Based on Progressive Training

doi:10.19678/j.issn.1000-3428.0065821

Abstract

Abstract:

The research on domain adaptive object detection based on adversarial training aims the deployment of detection models for use with different data sets without labeling new data sets. However, existing algorithms have difficulty in balancing the tasks of object detection and domain alignment. The general single discriminator structure is limited to single mode of data, resulting in degradation of domain alignment quality. This paper proposes a multi-discriminator domain adaptive object detection algorithm based on progressive training. Considering the limitations of the traditional single-discriminator structure in the domain alignment of complex structural data, a multi-discriminator structure is introduced into the instance-level domain-adaptive head to force it to consider multiple modes of data while learning the domain invariant information, which contributes to achieving higher quality and more comprehensive domain alignment. Meanwhile, to reduce the increased model complexity, a multi-discriminator structure designed to reuse the single discriminator parameters is introduced based on dropout technology. In this paper, an innovative progressive training strategy is introduced, whereby the proportion and difficulty of domain alignment are gradually increased with the progress in training, to dynamically balance the weight of object detection and domain alignment tasks. The experimental results indicate that the mean average precision of the algorithm in domain adaptation from Cityscapes to Foggy Cityscapes was 42.9%, which is an improvement of at least 0.5 percentage points compared to algorithms of recent years.

Key words: object detection, domain adaptive, adversarial training, multi-discriminator, progressive training strategy

摘要：

基于对抗训练的域适应目标检测的研究旨在不对新数据集进行额外标注的情况下, 将检测模型应用于不同的数据集。但现有算法存在目标检测和域对齐任务难以平衡的问题, 且一般的单判别器结构容易局限于数据的单个模式, 导致域对齐的质量下降。提出一种基于渐进式训练的多判别器域适应目标检测算法, 针对传统的单判别器结构对复杂结构数据进行域对齐时的局限性, 在实例级的域适应头中引入多判别器结构, 使其在学习域不变信息时考虑数据的多模结构, 实现质量更高、更全面的域对齐。同时, 为降低引入多判别器结构而增加的模型复杂度, 设计基于Dropout技术的多判别器结构, 对单个判别器参数进行重复利用, 并创新性地引入渐进式训练策略, 即随着训练的推进逐步增大域对齐任务的比重和难度, 动态平衡目标检测和域对齐任务的权重。实验结果表明, 所提算法在Cityscapes到Foggy Cityscapes的域适应场景下的平均检测精度为42.9%, 相比近几年该领域的新算法提高了至少0.5个百分点。

关键词: 目标检测, 域适应, 对抗训练, 多判别器, 渐进式训练策略

Huisen LI, Jin HOU, Hui DANG, Yuhang ZHOU. Domain Adaptive Multi-Discriminator Object Detection Based on Progressive Training[J]. Computer Engineering, 2023, 49(10): 202-211, 221.

李惠森, 侯进, 党辉, 周宇航. 基于渐进式训练的多判别器域适应目标检测[J]. 计算机工程, 2023, 49(10): 202-211, 221.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0065821

https://www.ecice06.com/EN/Y2023/V49/I10/202

Figures/Tables 14

Fig.1 Overall framework of the algorithm in this paper

Fig.2 Image level domain adaptive head

Fig.3 Instance level domain classifier

Fig.4 Instance level domain classifier based on Dropout

Fig.5 Multi-discriminator domain adaptation structure based on Dropout

Fig.6 Variation curve of

$ {\lambda } $

parameter with the iterations

Fig.7 P-R curves of different algorithms

Fig.8 Detection results comparison of differernt algorithms

Fig.9 Influence of the number of discriminators on model performance

Fig.10 Influence of

$ {\lambda } $

parameter on model performance

References 33

1	LI P L, CHEN X Z, SHEN S J. Stereo R-CNN based 3D object detection for autonomous driving[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2020: 7636-7644.
2	HATTORI H, LEE N, BODDETI V N, et al. Synthesizing a scene-specific pedestrian detector and pose estimator for static video surveillance. International Journal of Computer Vision, 2018, 126 (9): 1027- 1044. doi: 10.1007/s11263-018-1077-3
3	SCALISE R, THOMASON J, BISK Y, et al. Improving robot success detection using static object data[C]//Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. Washington D. C., USA: IEEE Press, 2020: 4229-4235.
4	邹慧海, 侯进. 改进SSD算法的道路小目标检测研究. 计算机工程, 2022, 48 (5): 281- 288. URL
	ZOU H H, HOU J. Research on road small target detection with improved SSD algorithm. Computer Engineering, 2022, 48 (5): 281- 288. URL
5	GOPALAN R, LI R N, CHELLAPPA R. Domain adaptation for object recognition: an unsupervised approach[C]//Proceedings of International Conference on Computer Vision. Washington D. C., USA: IEEE Press, 2012: 999-1006.
6	李莉, 王新强, 银珊. 基于衰减补偿与直方图拉伸的水下图像增强算法. 计算机工程, 2022, 48 (6): 222- 227. URL
	LI L, WANG X Q, YIN S. Underwater image enhancement algorithm based on attenuation compensation and histogram stretching. Computer Engineering, 2022, 48 (6): 222- 227. URL
7	GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems. New York, USA: ACM Press, 2014: 2672-2680.
8	REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39 (6): 1137- 1149. doi: 10.1109/TPAMI.2016.2577031
9	CAI Z W, VASCONCELOS N. Cascade R-CNN: delving into high quality object detection[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2018: 6154-6162.
10	HE K M, GKIOXARI G, DOLLÁR P, et al. Mask R-CNN[C]//Proceedings of IEEE International Conference on Computer Vision. Washington D. C., USA: IEEE Press, 2017: 2980-2988.
11	LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[C]//Proceedings of European Conference on Computer Vision. Berlin, Germany: Springer, 2016: 21-37.
12	REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2017: 6517-6525.
13	REDMON J, FARHADI A. YOLOv3: an incremental improvement[EB/OL]. [2022-08-08]. https://arxiv.org/abs/1804.02767.
14	BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection[EB/OL]. [2022-08-08]. https://arxiv.org/abs/2004.10934.
15	LONG M S, CAO Y, WANG J M, et al. Learning transferable features with deep adaptation networks[C]//Proceedings of the 32nd International Conference on Machine Learning. New York, USA: ACM Press, 2015: 97-105.
16	KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks. Communications of the ACM, 2017, 60 (6): 84- 90. doi: 10.1145/3065386
17	LI J J, CHEN E P, DING Z M, et al. Maximum density divergence for domain adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43 (11): 3918- 3930. doi: 10.1109/TPAMI.2020.2991050
18	CHEN Y H, LI W, SAKARIDIS C, et al. Domain adaptive faster R-CNN for object detection in the wild[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2018: 3339-3348.
19	SAITO K, USHIKU Y, HARADA T, et al. Strong-weak distribution alignment for adaptive object detection[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2020: 6949-6958.
20	XU M H, WANG H, NI B B, et al. Cross-domain detection via graph-induced prototype alignment[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2020: 12352-12361.
21	GUAN D Y, HUANG J X, XIAO A R, et al. Uncertainty-aware unsupervised domain adaptation in object detection. IEEE Transactions on Multimedia, 2022, 24, 2502- 2514. doi: 10.1109/TMM.2021.3082687
22	HE K M, ZHANG X Y, REN S Q, et al. Identity mappings in deep residual networks[C]//Proceedings of European Conference on Computer Vision. Berlin, Germany: Springer, 2016: 630-645.
23	GANIN Y, LEMPITSKY V. Unsupervised domain adaptation by backpropagation[EB/OL]. [2022-08-08]. https://arxiv.org/abs/1409.7495.
24	PEI Z Y, CAO Z J, LONG M S, et al. Multi-adversarial domain adaptation[C]//Proceedings of AAAI Conference on Artificial Intelligence. Menlo Park, USA: AAAI Press, 2018: 3934-3941.
25	KURMI V K, BAJAJ V, SUBRAMANIAN V K, et al. Curriculum based dropout discriminator for domain adaptation[EB/OL]. [2022-08-08]. https://arxiv.org/abs/1907.10628.
26	CORDTS M, OMRAN M, RAMOS S, et al. The cityscapes dataset for semantic urban scene understanding[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C., USA. IEEE Press, 2016: 3213-3223.
27	SAKARIDIS C, DAI D X, VAN GOOL L. Semantic foggy scene understanding with synthetic data. International Journal of Computer Vision, 2018, 126 (9): 973- 992. doi: 10.1007/s11263-018-1072-8
28	GEIGER A, LENZ P, URTASUN R. Are we ready for autonomous driving?The KITTI vision benchmark suite[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2012: 3354-3361.
29	PADILLA R, NETTO S L, DA SILVA E A B. A survey on performance metrics for object-detection algorithms[C]//Proceedings of International Conference on Systems, Signals and Image Processing. Washington D. C., USA: IEEE Press, 2020: 237-242.
30	HSU C C, TSAI Y H, LIN Y Y, et al. Every pixel matters: center-aware feature alignment for domain adaptive object detector[C]//Proceedings of European Conference on Computer Vision. Berlin, Germany: Springer, 2020: 733-748.
31	WANG W, CAO Y, ZHANG J, et al. Exploring sequence feature alignment for domain adaptive detection transformers[C]//Proceedings of the 29th ACM International Conference on Multimedia. New York, USA: ACM Press, 2021: 1730-1738.
32	LIU D N, ZHANG C Y, SONG Y, et al. Decompose to adapt: cross-domain object detection via feature disentanglement. IEEE Transactions on Multimedia, 2023, 25, 1333- 1344. doi: 10.1109/TMM.2022.3141614
33	ALQASIR H, MUSELET D, DUCOTTET C. Region proposal oriented approach for domain adaptive object detection[C]//Proceedings of International Conference on Advanced Concepts for Intelligent Vision Systems. Berlin, Germany: Springer, 2020: 38-50.

[1]	ZENG Yuqi, LIU Bo, ZHONG Baichang, ZHONG Jin. Student Classroom Behavior Detection Algorithm Based on Improved YOLOv8 in Smart Education [J]. Computer Engineering, 2024, 50(9): 344-355.
[2]	WANG Yanguo, LÜ Pengyuan, LAN Jinjiang, LIU Mingzhe, QIN Guanjun, ZHANG Shuohua, ZHOU Yu. Wind Turbine Fault Classification Method Based on Adversarial Training and Transformer [J]. Computer Engineering, 2024, 50(9): 377-384.
[3]	Xiangquan GUI, Shiqing LIU, Li LI, Qingsong QIN, Tangyan LI. Pedestrian Detection Algorithm for Scenic Spots Based on Improved YOLOv8 [J]. Computer Engineering, 2024, 50(7): 342-351.
[4]	WEI Zhuoyi, LUO Mai, LI Wenbing, ZENG Yuansong, YU Weijiang, YANG Yuedong. Intelligent Single-Cell Classification Based on Multisource Domain Adaptation [J]. Computer Engineering, 2024, 50(6): 48-55.
[5]	SUN Bangyong, MA Ming, YU Tao. Multi-scale Camouflaged Object Detection Method Based on Regional Feature Enhancement [J]. Computer Engineering, 2024, 50(5): 209-219.
[6]	ZHOU Qinyuan, DENG Yueping, ZHANG Lei, ZHANG Chen, LU Rirong, HU Xianzhe. Dynamic Visual SLAM System Integrating Optical Flow and Multi-View Geometry [J]. Computer Engineering, 2024, 50(5): 250-259.
[7]	ZHOU Zhaochen, FANG Qingmao, WU Xiaohong, HU Ping, HE Xiaohai. Machine Reading Comprehension Model Based on MacBERT and Adversarial Training [J]. Computer Engineering, 2024, 50(5): 41-50.
[8]	LIU Ruikang, LIU Weiming, DUAN Mengfei, XIE Wei, DAI Yuan. Metro Platform Foreign Object Detection Based on Dual-channel Transformer [J]. Computer Engineering, 2024, 50(4): 197-207.
[9]	YUAN Hao, GE Haibo, XIN Shiao, XU Dongmei, YANG Yudi. Edge Refinement Detection of Camouflage Targets Based on Deep Texture Features [J]. Computer Engineering, 2024, 50(10): 89-99.
[10]	REN Yi, SU Bo, YUAN Shuai. Multidimensional Feature Named Entity Recognition Method in Education Domain [J]. Computer Engineering, 2024, 50(10): 110-118.
[11]	WANG Feifan, CHEN Xi'ai, REN Weihong, GUAN Yu, HAN Zhi, TANG Yandong. Low-illumination Object-Detection Algorithm Based on Image Adaptive Enhancement [J]. Computer Engineering, 2024, 50(10): 352-361.
[12]	LAN Hong, WANG Huizhao. Combining Lightweight and Multiscale Fusion for Traffic Sign Detection Algorithm [J]. Computer Engineering, 2024, 50(10): 381-392.
[13]	Bingyan ZHU, Zhihua CHEN, Bin SHENG. Remote Sensing Image Detection Based on Perceptually Enhanced Swin Transformer [J]. Computer Engineering, 2024, 50(1): 216-223.
[14]	Xinlu JIANG, Tianen CHEN, Cong WANG, Chunjiang ZHAO. Small Object Detection Algorithm for Agricultural Pest Images in Field Environments [J]. Computer Engineering, 2024, 50(1): 232-241.
[15]	Wenshun SHENG, Xiongfeng YU, Jiayan LIN, Xin CHEN. Small-Scale Object Detection Algorithm Integrating Attention and Feature Pyramids [J]. Computer Engineering, 2024, 50(1): 242-250.

Please choose a citation manager

Content to export