特征互斥化的目标检测域适应方法

doi:10.3778/j.issn.1002-8331.2301-0103

摘要/Abstract

摘要： 当前，蒸馏学习已成为目标检测无监督域适应领域中的一种常用技术手段。然而蒸馏带来的特征偏移会导致目标域上伪标签的准确性较低，不利于目标域的精确检测。因此提出特征互斥化方法，包括特征分布互斥化和特征属性互斥化。其中特征分布互斥化鼓励网络对不同类别的特征分布进行互斥，特征属性互斥化促使分类器对不同类别主要使用的属性进行互斥。还提出强弱增强一致性方法对网络的预测输出进行一致性约束，促使网络提取的特征中主要包含与目标域检测相关的属性，进一步提高特征互斥化方法的效果。所提方法在多个域适应场景上进行了广泛的实验，在相同实验设置下的结果表明，所提方法较其他先进方法具有更好的有效性。

关键词: 目标检测, 无监督域适应, 蒸馏学习, 计算机视觉

Abstract: Recently, distillation learning has become a common technical means in the field of unsupervised object detection domain adaptation. However, due to the feature shift of distillation, the accuracy of the pseudo-labels obtained on the target domain is not so accurate, which has a certain negative impact on the target domain precise detection. Therefore, a feature mutual exclusion method is proposed, including feature distribution mutual exclusion and feature attribute mutual exclusion. The feature distribution mutual exclusion is used to prompt the feature distribution of different categories to be mutually exclusive, while the feature attribute mutual exclusion realizes that the classifiers mainly rely on mutual exclusive attributes when classifying different categories of features. In addition, a strong-weak augment consistency method is proposed to constrain the consistency of the network prediction, so that the features extracted by the network will mainly contain attributes related to the target domain detection, thereby improving the effect of the feature mutual exclusion method. Extensive experiments are conducted on several domain adaptation scenarios. The results show the effectiveness of the proposed method compared with other state-of-the-art methods under the same experimental settings.

Key words: object detection, unsupervised domain adaptation, distillation learning, computer vision

李润泽, 王子磊. 特征互斥化的目标检测域适应方法[J]. 计算机工程与应用, 2024, 60(10): 198-208.

LI Runze, WANG Zilei. Domain Adaptive Object Detection Method Based on Feature Mutual Exclusion[J]. Computer Engineering and Applications, 2024, 60(10): 198-208.

参考文献

[1] PAN S J, YANG Q. A survey on transfer learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2009, 22(10): 1345-1359.
[2] 邱颖豫, 张柯, 杨欣毅. 面向旋转机械故障诊断的深度流形迁移学习[J]. 计算机工程与应用, 2022, 58(12): 289-298.
QIU Y Y, ZHANG K, YANG X Y. Deep manifold transfer learning method for fault diagnosis of rotating machinery under different working conditions[J]. Computer Engineering and Applications, 2022, 58(12): 289-298.
[3] 赵鹏飞，李艳玲，林民. 结合胶囊网络的领域适应意图识别[J]. 计算机工程与应用, 2021, 57(21): 188-194.
ZHAO P F, LI Y L, LIN M. Intent detection of domain adaptation combined with capsule network[J]. Computer Engineering and Applications, 2021, 57(21): 188-194.
[4] CAI Q, PAN Y, NGO C W, et al. Exploring object relation in mean teacher for cross-domain detection[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 11457-11466.
[5] TARVAINEN A, VALPOLA H. Weight-averaged consistency targets improve semi-supervised deep learning results[J]. arXiv:1703.01780, 2017.
[6] DENG J, LI W, CHEN Y, et al. Unbiased mean teacher for cross-domain object detection[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 4091-4101.
[7] ZHU J Y, PARK T, ISOLA P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision, 2017: 2223-2232.
[8] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the 14th European Conference on Computer Vision. Cham: Springer, 2016: 21-37.
[9] 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, 2016: 779-788.
[10] REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems 28, 2015.
[11] TIAN Z, SHEN C, CHEN H, et al. FCOS: fully convolutional one-stage object detection[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019: 9627-9636.
[12] GE Z, LIU S, WANG F, et al. YOLOx: exceeding YOLO series in 2021[J]. arXiv:2107.08430, 2021.
[13] CARION N, MASSA F, SYNNAEVE G, et al. End-to-end object detection with transformers[C]//Proceedings of the 16th European Conference on Computer Vision. Cham: Springer, 2020: 213-229.
[14] LI F, ZHANG H, LIU S, et al. DN-DETR: accelerate DETR training by introducing query denoising[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 13619-13627.
[15] KIM T, JEONG M, KIM S, et al. Diversify and match: a domain adaptive representation learning paradigm for object detection[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 12456-12465.
[16] HSU H K, YAO C H, TSAI Y H, et al. Progressive domain adaptation for object detection[C]//Proceedings of the 2020 IEEE/CVF Winter Conference on Applications of Computer Vision, 2020: 749-757.
[17] CHEN Y, LI W, SAKARIDIS C, et al. Domain adaptive faster R-CNN for object detection in the wild[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018: 3339-3348.
[18] SAITO K, USHIKU Y, HARADA T, et al. Strong-weak distribution alignment for adaptive object detection[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 6956-6965.
[19] HE Z, ZHANG L. Multi-adversarial Faster-RCNN for unrestricted object detection[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019: 6668-6677.
[20] CHEN C, ZHENG Z, DING X, et al. Harmonizing transferability and discriminability for adapting object detectors[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 8869-8878.
[21] CHEN C, ZHENG Z, HUANG Y, et al. I3Net: implicit instance-invariant network for adapting one-stage object detectors[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 12576-12585.
[22] LI C, DU D, ZHANG L, et al. Spatial attention pyramid network for unsupervised domain adaptation[C]//Proceedings of the 16th European Conference on Computer Vision, Glasgow, 2020: 481-497.
[23] VS V, GUPTA V, OZA P, et al. Mega-CDA: memory guided attention for category-aware unsupervised domain adaptive object detection[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 4516-4526.
[24] ZHANG Y, WANG Z, MAO Y. RPN prototype alignment for domain adaptive object detector[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 12425-12434.
[25] CHEN C, LI J, ZHENG Z, et al. Dual bipartite graph learning: a general approach for domain adaptive object detection[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021: 2703-2712.
[26] WANG Y, ZHANG R, ZHANG S, et al. Domain-specific suppression for adaptive object detection[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 9603-9612.
[27] WU A, LIU R, HAN Y, et al. Vector-decomposed disentanglement for domain-invariant object detection[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021: 9342-9351.
[28] REZAEIANARAN F, SHETTY R, ALJUNDI R, et al. Seeking similarities over differences: similarity-based domain alignment for adaptive object detection[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021: 9204-9213.
[29] ZHAO L, WANG L. Task-specific inconsistency alignment for domain adaptive object detection[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 14217-14226.
[30] LI W, LIU X, YUAN Y. SIGMA: semantic-complete graph matching for domain adaptive object detection[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 5291-5300.
[31] ZHOU W, DU D, ZHANG L, et al. Multi-granularity alignment domain adaptation for object detection[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 9581-9590.
[32] YU J, LIU J, WEI X, et al. Cross-domain object detection with mean-teacher transformer[J]. arXiv:2205.01643, 2022.
[33] XU C D, ZHAO X R, JIN X, et al. Exploring categorical regularization for domain adaptive object detection[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 11724-11733.
[34] GANIN Y, USTINOVA E, AJAKAN H, et al. Domain-adversarial training of neural networks[J]. The Journal of Machine Learning Research, 2016, 17(1): 2096-2130.
[35] KIM S, CHOI J, KIM T, et al. Self-training and adversarial background regularization for unsupervised domain adaptive one-stage object detection[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019: 6092-6101.