实例分割方法研究综述

doi:10.3778/j.issn.1673-9418.2209051

摘要/Abstract

摘要： 近年来，随着计算水平的不断提高，基于深度学习的实例分割方法的研究取得了巨大的突破。图像实例分割可以区分图像中同一类的不同实例，是计算机视觉领域的重要研究方向，具有十分广阔的研究前景，在场景理解、医学图像分析、机器视觉、增强现实、图像压缩和视频监控等方面取得了巨大的实际应用价值。近年来，实例分割方法的更新频率越来越高，但目前很少有文献全面系统地分析实例分割相关研究背景。对基于深度学习的图像实例分割方法进行了全面系统的分析与总结，首先，介绍目前实例分割中常用的公共数据集与评价指标，并对现有数据集面临的挑战进行了分析；其次，分别从两阶段分割方法与单阶段分割方法的特性上对实例分割算法进行梳理与总结，阐述其核心思想与设计思路，并对这两类方法的优势与不足进行总结；然后，在公共数据集上评估这些模型的分割精度和速度；最后，总结目前实例分割面临的困难与挑战，以及面对挑战的解决思路，并对未来的研究方向进行展望。

关键词: 实例分割, 深度学习, 计算机视觉, 图像分割

Abstract: In recent years, with the continuous improvement of computing level, the research of instance segment-ation methods based on deep learning has made great breakthroughs. Image instance segmentation can distinguish different instances of the same class in images, which is an important research direction in the field of computer vision with broad research prospects, and has achieved great actual application value in scene comprehension, medical image analysis, machine vision, augmented reality, image compression, video monitoring, etc. Recently, instance segmentation methods have been updated more and more frequently, but there is a little literature to comprehensively and systematically analyze the research background related to instance segmentation. This paper provides a comprehensive and systematic analysis and summary of the image instance segmentation methods based on deep learning. Firstly, this paper introduces the currently used common public datasets and evaluation indexes in instance segmentation, and analyzes the challenges of current datasets. Secondly, this paper respectively combs and summarizes the instance segmentation algorithms in the characteristics of two-stage segmentation methods and single-stage segmentation methods, elaborates their central ideas and design thoughts, and summarizes the advantages and shortcomings of the two types of methods. Thirdly, this paper evaluates the segmentation accuracy and speed of the models on a public dataset. Finally, this paper summarizes the current difficulties and challenges of instance segmentation, presents the solution ideas for facing the challenges, and makes a prospect for future research directions.

Key words: instance segmentation, deep learning, computer vision, image segmentation

黄涛, 李华, 周桂, 李少波, 王阳. 实例分割方法研究综述[J]. 计算机科学与探索, 2023, 17(4): 810-825.

HUANG TAO, LI Hua, ZHOU Gui, LI Shaobo, WANG Yang. Survey of Research on Instance Segmentation Methods[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(4): 810-825.

参考文献

[1] LIN G, MILAN A, SHEN C, et al. RefineNet: multi-path refinement networks for high-resolution semantic segment-ation[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 5168- 5177.
[2] ZHAO Z Q, ZHENG P, XU S, et al. Object detection with deep learning: a review[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019, 30(11): 3212-3232.
[3] MINAEE S, BOYKOV Y Y, PORIKLI F, et al. Image segm-entation using deep learning: a survey[J]. IEEE Transac-tions on Pattern Analysis and Machine Intelligence, 2022, 44(7): 3523-3542.
[4] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]// Proceedings of the 26th Annual Conference on Neural Information Processing Systems 2012, Lake Tahoe, Dec 3-6, 2012. Red Hook: Curran Associates, 2012: 1106-1114.
[5] LIU H, YANG G, YANG L, et al. Anchor-based manifold binary pattern for finger vein recognition[J]. Science China Information Sciences, 2019, 62(5): 52104.
[6] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: common objects in context[C]//LNCS 8693: Proceedings of the 13th European Conference on Computer Vision, Zurich, Sep 6-12, 2014. Cham: Springer, 2014: 740-755.
[7] CORDTS M, OMRAN M, RAMOS S, et al. The cityscapes dataset for semantic urban scene understanding[C]//Proce-edings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Jun 27-30, 2016. Wash-ington: IEEE Computer Society, 2016: 3213-3223.
[8] NEUHOLD G, OLLMANN T, ROTA BULO S, et al. The mapillary vistas dataset for semantic understanding of street scenes[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision, Venice, Oct 22-29, 2017. Washington: IEEE Computer Society, 2017: 5000-5009.
[9] GUPTA A, DOLLAR P, GIRSHICK R. LVIS: a dataset for large vocabulary instance segmentation[C]//Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, Jun 16-20, 2019. Piscataway: IEEE, 2019: 5356-5364.
[10] KUZNETSOVA A, ROM H, ALLDRIN N, et al. The open images dataset V4[J]. International Journal of Computer Vision, 2020, 128(7): 1956-1981.
[11] 苏丽, 孙雨鑫, 苑守正. 基于深度学习的实例分割研究综述[J]. 智能系统学报, 2021, 17(1): 16-31.
SU L, SUN Y X, YUAN S Z. A survey of instance segmentation research based on deep learning[J]. CAAI Transactions on Intelligent Systems, 2021, 17(1): 16-31.
[12] 张继凯, 赵君, 张然, 等. 深度学习的图像实例分割方法综述[J]. 小型微型计算机系统, 2021, 42(1): 161-171.
ZHANG J K, ZHAO J, ZHANG R, et al. Survey of image instance segmentation methods using deep learning[J]. Journal of Chinese Computer Systems, 2021, 42(1): 161-171.
[13] HARIHARAN B, ARBELáEZ P, GIRSHICK R, et al. Simultaneous detection and segmentation[C]//LNCS 8695: Proceedings of the 13th European Conference on Computer Vision, Zurich, Sep 6-12, 2014. Cham: Springer, 2014: 297-312.
[14] ARBELáEZ P, PONT-TUSET J, BARRON J T, et al. Multi-scale combinatorial grouping[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, Jun 23-28, 2014. Washington: IEEE Computer Society, 2014: 328-335.
[15] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[16] HART P E, STORK D G, DUDA R O. Pattern classification[M]. New York: John Wiley & Sons, 2000.
[17] NEUBECK A, VAN GOOL L. Efficient non-maximum supp-ression[C]//Proceedings of the 18th International Conference on Pattern Recognition, Hong Kong, China, Aug 20-24, 2006. Washington: IEEE Computer Society, 2006: 850-855.
[18] PINHEIRO P O, COLLOBERT R, DOLLáR P. Learning to segment object candidates[J]. arXiv:1506.06204, 2015.
[19] PINHEIRO P O, LIN T Y, COLLOBERT R, et al. Learning to refine object segments[C]//LNCS 9905: Proceedings of the 14th European Conference on Computer Vision, Amste-rdam, Oct 11-14, 2016. Cham: Springer, 2016: 75-91.
[20] 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, Columbus, Jun 23-28, 2014. Washington: IEEE Computer Society, 2014: 580-587.
[21] LIU L, OUYANG W, WANG X, et al. Deep learning for generic object detection: a survey[J]. International Journal of Computer Vision, 2020, 128(2): 261-318.
[22] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Image-Net classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[23] GIRSHICK R, DONAHUE J, DARRELL T, et al. Region-based convolutional networks for accurate object detection and segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 38(1): 142-158.
[24] GIRSHICK R. Fast R-CNN[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision, Santiago, Dec 7-13, 2015. Washington: IEEE Computer Society, 2015: 1440- 1448.
[25] WANG X, SHRIVASTAVA A, GUPTA A. A-fast-RCNN: hard positive generation via adversary for object detection[C]//Proceedings of the 2017 IEEE Conference on Comp-uter Vision and Pattern Recognition, Honolulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 2606-2615.
[26] LI J, LIANG X, SHEN S M, et al. Scale-aware fast R-CNN for pedestrian detection[J]. IEEE Transactions on Multi-media, 2017, 20(4): 985-996.
[27] 黄继鹏, 史颖欢, 高阳. 面向小目标的多尺度Faster-RCNN 检测算法[J]. 计算机研究与发展, 2019, 56(2): 319-327.
HUANG J P, SHI Y H, GAO Y. Multi-scale Faster-RCNN algorithm for small object detection[J]. Journal of Computer Research and Development, 2019, 56(2): 319-327.
[28] MOESLUND T B, GRANUM E. A survey of computer vision-based human motion capture[J]. Computer Vision and Image Understanding, 2001, 81(3): 231-268.
[29] WANG K, DONG Y, BAI H, et al. Use fast R-CNN and cascade structure for face detection[C]//Proceedings of the 2016 Visual Communications and Image Processing, Chengdu, Nov 27-30, 2016. Piscataway: IEEE, 2016: 1-4.
[30] HSU S C, HUANG C L, CHUANG C H. Vehicle detection using simplified fast R-CNN[C]//Proceedings of the 2018 International Workshop on Advanced Image Technology， Chiang Mai, Jan 7-9, 2018. Piscataway: IEEE, 2018: 1-3.
[31] 任少卿. 基于特征共享的高效物体检测[D]. 合肥: 中国科学技术大学, 2016.
REN S Q. Efficient object detection based on feature shar-ing[D]. Hefei: University of Science and Technology of China, 2016.
[32] ZHU C, ZHENG Y, LUU K, et al. CMS-RCNN: contextual multi-scale region-based CNN for unconstrained face detec-tion[M]//BHANU B, KUMAR A. Deep Learning for Bio-metrics. Berlin, Heidelberg: Springer, 2017: 57-79.
[33] UIJLINGS J R R, VAN DE SANDE K E A, GEVERS T,   et al. Selective search for object recognition[J]. Interna-tional Journal of Computer Vision, 2013, 104(2): 154-171.
[34] VAN DE SANDE K E A, UIJLINGS J R R, GEVERS T,   et al. Segmentation as selective search for object recognit-ion[C]//Proceedings of the 2011 IEEE International Confe-rence on Computer Vision, Barcelona, Nov 6-13, 2011. Wash-ington: IEEE Computer Society, 2011: 1879-1886.
[35] K?HLER C, SOFKA W, GRIMPE C. Selective search, sectoral patterns, and the impact on product innovation performance[J]. Research Policy, 2012, 41(8): 1344-1356.
[36] REN S Q, HE K M, GIRSHICK R B, et al. Faster R-CNN: towards real-time object detection with region proposal net-works[C]//Proceedings of the Annual Conference on Neural Information Processing Systems 2015, Montreal, Dec 7-12, 2015. Red Hook: Curran Associates, 2015: 91-99.
[37] TANG P, WANG X, WANG A, et al. Weakly supervised region proposal network and object detection[C]//LNCS 11215: Proceedings of the 15th European Conference on Computer Vision, Munich, Sep 8-14, 2018. Cham: Springer, 2018: 370-386.
[38] HE K M, GKIOXARI G, DOLLáR P, et al. Mask R-CNN[C]//Proceedings of the 2017 IEEE International Confer-ence on Computer Vision, Venice, Oct 22-29, 2017. Washin-gton: IEEE Computer Society, 2017: 2980-2988.
[39] 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 Recogn-ition, Las Vegas, Jun 27-30, 2016. Washington: IEEE Com-puter Society, 2016: 770-778.
[40] LIN T Y, DOLLáR P, GIRSHICK R B, et al. Feature pyramid networks for object detection[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 936-944.
[41] LONG J, SHELHAMER E, DARRELL T. Fully convol-utional networks for semantic segmentation[J]. IEEE Tran-sactions on Pattern Analysis and Machine Intelligence, 2015, 39(4): 640-651.
[42] DAI J F, HE K M, LI Y, et al. Instance-sensitive fully conv-olutional networks[C]//LNCS 9910: Proceedings of the 14th European Conference on Computer Vision, Amsterdam, Oct 11-14, 2016. Cham: Springer, 2016: 534-549.
[43] VUOLA A O, AKRAM S U, KANNALA J. Mask-RCNN and U-Net ensembled for nuclei segmentation[C]//Proceedings of the 2019 IEEE 16th International Symposium on Biomedical Imaging, Venice, Apr 8-11, 2019. Piscataway: IEEE, 2019: 208-212.
[44] CHEN L C, HERMANS A, PAPANDREOU G, et al. Mask-Lab: instance segmentation by refining object detection with semantic and direction features[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Jun 18-22, 2018. Washington:IEEE Computer Society, 2018: 4013-4022.
[45] LIU S, QI L, QIN H, et al. Path aggregation network for instance segmentation[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Jun 18-22, 2018. Washington: IEEE Comp-uter Society, 2018: 8759-8768.
[46] KIM S W, KOOK H K, SUN J Y, et al. Parallel feature pyramid network for object detection[C]//LNCS 11209: Proceedings of the 15th European Conference on Computer Vision, Munich, Sep 8-14, 2018. Cham Springer, 2018: 239-256.
[47] GONG T, CHEN K, WANG X, et al. Temporal ROI align for video object recognition[C]//Proceedings of the 35th AAAI Conference on Artificial Intelligence, the 33rd Conference on Innovative Applications of Artificial Intelli-gence, the 11th Symposium on Educational Advances in Artificial Intelligence, Feb 2-9, 2021. Menlo Park: AAAI, 2021: 1442-1450.
[48] VU T, KANG H, YOO C D. SCNet: training inference sample consistency for instance segmentation[C]//Procee-dings of the 35th AAAI Conference on Artificial Intellig-ence, the 33rd Conference on Innovative Applications of Artificial Intelligence, the 11th Symposium on Educational Advances in Artificial Intelligence, Feb 2-9, 2021. Menlo Park: AAAI, 2021: 2701-2709.
[49] ZANG Y H, HUANG C, LOY C C. FASA: feature augmen-tation and sampling adaptation for long-tailed instance segm-entation[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, Montreal, Oct 10-17, 2021. Piscataway: IEEE, 2021: 3437-3446.
[50] TIAN Z, SHEN C H, WANG X L, et al. BoxInst: high-perf-ormance instance segmentation with box annotations[C]//Proceedings of the 2021 IEEE Conference on Computer Vision and Pattern Recognition, Jun 19-25, 2021. Piscat-away: IEEE, 2021: 5443-5452.
[51] ZHANG G, LU X, TAN J R, et al. RefineMask: towards high-quality instance segmentation with fine-grained feat-ures[C]//Proceedings of the 2021 IEEE Conference on Computer Vision and Pattern Recognition, Jun 19-25, 2021. Piscataway: IEEE, 2021: 6861-6869.
[52] LIU S, JIA J Y, FIDLER S, et al. SGN: sequential grouping networks for instance segmentation[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision, Venice, Oct 22-29, 2017. Washington: IEEE Computer Society, 2017: 3516-3524.
[53] GAO N Y, SHAN Y H, WANG Y P, et al. SSAP: single-shot instance segmentation with affinity pyramid[C]//Proce-edings of the 2019 IEEE/CVF International Conference on Computer Vision, Seoul, Oct 27-Nov 2, 2019. Piscataway: IEEE, 2019: 642-651.
[54] DE BRABANDERE B, NEVEN D, VAN GOOL L. Sema-ntic instance segmentation with a discriminative loss funct-ion[J]. arXiv:1708.02551, 2017.
[55] FATHI A, WOJNA Z, RATHOD V, et al. Semantic instance segmentation via deep metric learning[J]. arXiv:1703.10277, 2017.
[56] KE L, DANELLJAN M, LI X, et al. Mask transfiner for high-quality instance segmentation[J]. arXiv:2111.13673, 2021.
[57] FINKEL R A, BENTLEY J L. Quad trees a data structure for retrieval on composite keys[J]. Acta Informatica, 1974, 4(1): 1-9.
[58] HU J, CAO L, LU Y, et al. ISTR: end-to-end instance segm-entation with transformers[J]. arXiv:2105.00637, 2021.
[59] BOLYA D, ZHOU C, XIAO F, et al. YOLACT: real-time instance segmentation[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, Seoul, Oct 27-Nov 2, 2019. Piscataway: IEEE, 2019: 9156-9165.
[60] BOLYA D, ZHOU C, XIAO F, et al. YOLACT++: better real-time instance segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 44(2): 1108-1121.
[61] DAI J F, QI H Z, XIONG Y W, et al. Deformable convo-lutional networks[C]//Proceedings of the 2017 IEEE Intern-ational Conference on Computer Vision, Venice, Oct 22-29, 2017. Washington: IEEE Computer Society, 2017: 764-773.
[62] HURTIK P, MOLEK V, HULA J, et al. Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3[J]. Neural Computing and Applications, 2022, 34(10): 8275-8290.
[63] WANG X H, ZHAO K, ZHANG R X, et al. ContrastMask: contrastive learning to segment every thing[C]//Procee-dings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, Jun 18-24, 2022. Piscataway: IEEE, 2022: 11594-11603.
[64] XIE E Z, SUN P Z, SONG X G, et al. PolarMask: single shot instance segmentation with polar representation[C]//Proceedings of the 2020 IEEE/CVF Conference on Comp-uter Vision and Pattern Recognition, Seattle, Jun 13-19, 2020. Piscataway: IEEE, 2020: 12190-12199.
[65] GóMEZ L, KARATZAS D. Textproposals: a text-specific selective search algorithm for word spotting in the wild[J]. Pattern Recognition, 2017, 70: 60-74.
[66] WANG X L, KONG T, SHEN C H, et al. SOLO: segm-enting objects by locations[C]//LNCS 12363: Proceedings of the 16th European Conference on Computer Vision, Glasgow, Aug 23-28, 2020. Cham: Springer, 2020: 649-665.
[67] 李晓筱, 胡晓光, 王梓强, 等. 基于深度学习的实例分割研究进展[J]. 计算机工程与应用, 2021, 57(9): 60-67.
LI X X, HU X G, WANG Z Q, et al. Survey of instance segmentation based on deep learning[J]. Computer Engin-eering and Applications, 2021, 57(9): 60-67.
[68] ZENG L, SABAH M. EOLO: embedded object segment-ation only look once[J]. arXiv:2004.00123, 2020.
[69] WANG X, ZHANG R, KONG T, et al. SOLOv2: dynamic and fast instance segmentation[J]. arXiv:2003.10152, 2020.
[70] CHEN X L, GIRSHICK R B, HE K M, et al. TensorMask: a foundation for dense object segmentation[C]//Procee-dings of the 2019 IEEE/CVF International Conference on Computer Vision, Seoul, Oct 27-Nov 2, 2019. Piscataway:IEEE, 2019: 2061-2069.
[71] CHEN H, SUN K, TIAN Z, et al. BlendMask: top-down meets bottom-up for instance segmentation[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, Jun 13-19, 2020. Piscataway: IEEE, 2020: 8570-8578.
[72] TIAN Z, SHEN C H, CHEN H, et al. FCOS: fully convol-utional one-stage object detection[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, Seoul, Oct 27-Nov 2, 2019. Piscataway: IEEE, 2019: 9626-9635.
[73] KIRILLOV A, WU Y, HE K, et al. PointRend: image segmentation as rendering[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, Jun 13-19, 2020. Piscataway: IEEE, 2020: 9796-9805.
[74] SURESHA M, KUPPA S, RAGHUKUMAR D S. Point-Rend segmentation for a densely occluded moving object in a video[C]//Proceedings of the 2021 4th International Conference on Computational Intelligence and Communication Technologies, Sonepat, Jul 3, 2021. Piscataway: IEEE, 2021: 282-287.
[75] FANG Y, YANG S, WANG X, et al. QueryInst: parallelly supervised mask query for instance segmentation[J]. arXiv: 2105.01928, 2021.
[76] ZHANG T, WEI S Q, JI S P. E2EC: an end-to-end contour-based method for high-quality high-speed instance segmen-tation[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans,Jun 18-24, 2022. Piscataway: IEEE, 2022: 4433-4442.
[77] SHAFIQ M, GU Z. Deep residual learning for image recognition: a survey[J]. Applied Sciences, 2022, 12(18): 8972.
[78] QI L, WANG Y, CHEN Y, et al. PointINS: point-based inst-ance segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(10): 6377-6392.
[79] YAN Z, YANG X, CHENG K T. Enabling a single deep learning model for accurate gland instance segmentation: a shape-aware adversarial learning framework[J]. IEEE Tran-sactions on Medical Imaging, 2020, 39(6): 2176-2189.
[80] NURMAINI S, RACHMATULLAH M N, SAPITRI A I,   et al. Accurate detection of septal defects with fetal ultra-sonography images using deep learning-based multiclass inst-ance segmentation[J]. IEEE Access, 2020, 8: 196160-196174.
[81] LU J, JIA H, LI T, et al. An instance segmentation based framework for large-sized high-resolution remote sensing images registration[J]. Remote Sensing, 2021, 13(9): 1657.
[82] SU H, WEI S, LIU S, et al. HQ-ISNet: high-quality instance segmentation for remote sensing imagery[J]. Remote Sensing, 2020, 12(6): 989.
[83] KUMAR D, ZHANG X L. Improving more instance segmentation and better object detection in remote sensing imagery based on cascade mask R-CNN[C]//Proceedings of the 2021 IEEE International Geoscience and Remote Sensing Symposium, Brussels, Jul 11-16, 2021. Piscataway: IEEE, 2021: 4672-4675.
[84] WU Z, HOU B, REN B, et al. A deep detection network based on interaction of instance segmentation and object detection for SAR images[J]. Remote Sensing, 2021, 13(13): 2582.
[85] ZHANG T, ZHANG X. A mask attention interaction and scale enhancement network for SAR ship instance segmen-tation[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 1-5.
[86] LI Q Y, MOU L C, HUA Y S, et al. Instance segmentation of buildings using keypoints[C]//Proceedings of the 2020 IEEE nternational Geoscience and Remote Sensing Symp-osium, Waikoloa, Sep 26-Oct 2, 2020. Piscataway: IEEE,2020: 1452-1455.
[87] FANG X, LI Q, ZHU J, et al. Sewer defect instance segm-entation, localization, and 3D reconstruction for sewer floating capsule robots[J]. Automation in Construction, 2022, 142: 104494.
[88] TU Z, WU S, KANG G, et al. Real-time defect detection of track components: considering class imbalance and subtle difference between classes[J]. IEEE Transactions on Instru-mentation and Measurement, 2021, 70: 1-12.
[89] LI B, WANG T, HU Z D, et al. Two-level model for detec-ting substation defects from infrared images[J]. Sensors, 2022, 22(18): 6861.
[90] XU Y, LI D, XIE Q, et al. Automatic defect detection and segmentation of tunnel surface using modified Mask R-CNN[J]. Measurement, 2021, 178: 109316.
[91] ROSAS-ARIAS L, BENITEZ-GARCIA G, PORTILLO-PORTILLO J, et al. Fast and accurate real-time semantic segmentation with dilated asymmetric convolutions[C]//Proceedings of the 25th International Conference on Pattern Recognition, Milan, Jan 10-15, 2021. Piscataway: IEEE, 2021: 2264-2271.
[92] DING X F, SHEN C M, CHE Z P, et al. SCARF: a semantic constrained attention refinement network for semantic segmentation[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, Montreal, Oct 11-17, 2021. Piscataway: IEEE， 2021: 3002-3011.
[93] MORDAN T, THOME N, HENAFF G, et al. End-to-end learning of latent deformable part-based representations for object detection[J]. International Journal of Computer Vision, 2019, 127(11): 1659-1679.
[94] LI G F, YANG Y F, QU X D. Deep learning approaches on pedestrian detection in hazy weather[J]. IEEE Transactions on Industrial Electronics, 2019, 67(10): 8889-8899.
[95] ZHUANG F Z, QI Z Y, DUAN K Y, et al. A comprehensive survey on transfer learning[J]. Proceedings of the IEEE, 2020, 109(1): 43-76.
[96] FANG H S, SUN J H, WANG R Z, et al. InstaBoost: boosting instance segmentation via probability map guided copy-pasting[C]//Proceedings of the 2019 IEEE/CVF Inter-national Conference on Computer Vision, Seoul, Oct 27-Nov 2, 2019. Piscataway: IEEE, 2019: 682-691.
[97] GHIASI G, CUI Y, SRINIVAS A, et al. Simple copy-paste is a strong data augmentation method for instance segmen-tation[C]//Proceedings of the 2021 IEEE Conference on Computer Vision and Pattern Recognition, Jun 19-25, 2021. Piscataway: IEEE, 2021: 2918-2928.
[98] CHEN L C, ZHU Y K, PAPANDREOU G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//LNCS 11211: Proceedings of the 15th European Conference on Computer Vision, Munich, Sep 8-14, 2018. Cham: Springer, 2018: 833-851.
[99] XIAN Y Q, CHOUDHURY S, HE Y, et al. Semantic proj-ection network for zero-and few-label semantic segmen-tation[C]//Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, Jun 16-20, 2019. Piscataway: IEEE, 2019: 8256-8265.