SAM及其改进模型在图像分割中的应用综述

doi:10.19678/j.issn.1000-3428.0070619

摘要/Abstract

摘要：

随着通用人工智能技术的快速发展，基础模型在多个领域的应用日益受到广泛关注。在图像分割领域，分割一切模型(SAM)作为一种核心基础模型，在提升图像理解和处理效率方面展现出了显著优势。尽管SAM在图像分割任务中表现出色，但在功耗、计算效率以及在不同应用场景中的适应性等方面，仍然存在一定的优化空间。为此，从多个维度对SAM的改进方向进行了深入探索，包括提升速度与计算效率、增强模型的精度与鲁棒性、提高模型的适应性与通用性、优化提示工程设计，以及提升数据利用效率与强化迁移学习能力等方面。通过这些改进，SAM不仅能够在更复杂的任务中保持高效性能，还能更好地适应各领域和应用场景的需求。在此基础上，总结SAM在医学、遥感、机械等领域中的实际应用，展示了其在不同场景下的适用性与挑战。此外，详细介绍了图像分割领域常用的数据集和评价指标，通过实验对比分析，进一步评估了视觉Transformer(ViT)变体对SAM性能的影响，以及EfficientSAM、EfficientViT-SAM、MobileSAM和RobustSAM等改进模型的性能表现。最后，总结了SAM及其改进模型在实际应用中面临的挑战，并展望了未来的发展方向，旨在帮助科研工作者更全面地了解SAM及其变体的改进与应用，为新模型的提出提供启发。

关键词: 分割一切模型, 视觉基础模型, 改进模型, 图像分割, 通用模型

Abstract:

With the rapid advancement of general artificial intelligence technology, the application of foundational models across various fields has gained increasing attention. In image segmentation, the Segment Anything Model (SAM), as a foundational model, demonstrates notable advantages in enhancing image comprehension and processing efficiency. While SAM achieves state-of-the-art performance in image segmentation, further optimization in power consumption, computational efficiency, and cross-domain adaptability is required. This review provides an in-depth exploration of the potential improvements to SAM across several crucial dimensions, such as enhancing speed and computational efficiency, improving model accuracy and robustness, increasing adaptability and generalization, optimizing prompt engineering, and boosting data utilization and transfer learning capabilities. With these enhancements, SAM is expected to sustain high efficiency in highly complex tasks and better meet requirements of various fields and application contexts. In addition, this review summarizes the practical applications of SAM in various fields, including medical imaging, remote sensing, and the mechanical industry, and demonstrates the suitability and challenges of the model in different scenarios. Moreover, this review provides a detailed overview of commonly used datasets and evaluation metrics in the field of image segmentation. Through experimental comparative analyses, the impact of Vision Transformer (ViT) variants on the performance of SAM is assessed, along with performance evaluations of enhanced models, such as EfficientSAM, EfficientViT-SAM, MobileSAM, and RobustSAM. The challenges faced by SAM and its improved models in real-world applications are also discussed, and future research directions are proposed. This review aims to provide researchers with a comprehensive understanding of the advancements and applications of SAM and its variants, offering insights that may inform the development of new models.

Key words: Segment Anything Model (SAM), Vision Foundation Model (VFM), improved model, image segmentation, general model

马依拉木·木斯得克, 高雨欣, 张思拓, 冯珂, 阿布都克力木·阿布力孜, 哈里旦木·阿布都克里木. SAM及其改进模型在图像分割中的应用综述[J]. 计算机工程, 2025, 51(8): 16-38.

Mayilamu Musideke, GAO Yuxin, ZHANG Situo, FENG Ke, Abudukelimu Abulizi, Halidanmu Abudukelimu. Review of Application of SAM and Its Improved Models in Image Segmentation[J]. Computer Engineering, 2025, 51(8): 16-38.

https://www.ecice06.com/CN/Y2025/V51/I8/16

图/表 24

图1 SAM网络结构

Fig.1 Network structure of SAM

图2 SAM不同提示类型的示例

Fig.2 Examples of different prompt types in SAM

图3 FastSAM框架

Fig.3 Framework of FastSAM

图4 MobileSAM框架

Fig.4 Framework of MobileSAM

图5 HQ-SAM框架

Fig.5 Framework of HQ-SAM

图6 RobustSAM框架

Fig.6 Framework of RobustSAM

图7 Med-SA框架

Fig.7 Framework of Med-SA

图8 SAM-Adapter框架

Fig.8 Framework of SAM-Adapter

图9 HRSAM框架

Fig.9 Framework of HRSAM

图10 RSPrompter框架

Fig.10 Framework of RSPromp

图11 PerSAM框架

Fig.11 Framework of PerSAM

图12 SSM-SAM框架

Fig.12 Framework of SSM-SAM

图13 WS-SAM框架

Fig.13 Framework of WS-SAM

图14 ASAM框架

Fig.14 Framework of ASAM

图15 ViT-H版本SAM在不同数据集上的分割示例

Fig.15 Segmentation examples of the ViT-H version SAM on different datasets

参考文献 100

1	BOMMASANI R, HUDSON D A, ADELI E, et al. On the opportunities and risks of foundation models[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2108.07258v3.
2	DUBEY A, JAUHRI A, PANDEY A, et al. The Llama 3 herd of models[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2407.21783.
3	ACHIAM J, ADLER S, AGARWAL S, et al. GPT-4 technical report[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2303.08774.
4	赵欣, 李森, 李智生. 基于CNN和Transformer并行编码的腹部多器官图像分割. 吉林大学学报(理学版), 2024, 62 (5): 1145- 1154.
	ZHAO X , LI S , LI Z S . Abdominal multi-organ image segmentation based on parallel coding of CNN and Transformer. Journal of Jilin University (Science Edition), 2024, 62 (5): 1145- 1154.
5	WANG H Y, GUO S Z, YE J, et al. SAM-Med3D: towards general-purpose segmentation models for volumetric medical images[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2310.15161v3.
6	PANDEY S, CHEN K F, DAM E B. Comprehensive multimodal segmentation in medical imaging: combining YOLOv8 with SAM and HQ-SAM models[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). Washington D.C., USA: IEEE Press, 2023: 2584-2590.
7	PARULEKAR B , SINGH N , RAMIYA A M . Evaluation of Segment Anything Model (SAM) for automated labelling in machine learning classification of UAV geospatial data. Earth Science Informatics, 2024, 17 (5): 4407- 4418. doi: 10.1007/s12145-024-01402-7
8	HETANG C R, XUE H R, LE C, et al. Segment anything model for road network graph extraction[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Washington D.C., USA: IEEE Press, 2024: 2556-2566.
9	ZHAO X Q , WU Z , CHEN Y B , et al. Fine-grained high-resolution remote sensing image change detection by SAM-U-Net change detection model. Remote Sensing, 2024, 16 (19): 3620. doi: 10.3390/rs16193620
10	ZHANG J J, BAI C J, HE H R, et al. SAM-E: leveraging visual foundation model with sequence imitation for embodied manipulation[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2405.19586v1.
11	CHENG Y M, LI L L, XU Y Y, et al. Segment and track anything[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2305.06558v1.
12	AHMADI M, LONBAR A G, NAEINI H K, et al. Application of segment anything model for civil infrastructure defect assessment[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2304.12600v2.
13	KIRILLOV A, MINTUN E, RAVI N, et al. Segment anything[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Washington D.C., USA: IEEE Press, 2023: 3992-4003.
14	ZHANG Y C , SHEN Z R , JIAO R S . Segment anything model for medical image segmentation: current applications and future directions. Computers in Biology and Medicine, 2024, 171, 108238. doi: 10.1016/j.compbiomed.2024.108238
15	王淼, 黄智忠, 何晖光, 等. 分割一切模型SAM的潜力与展望: 综述. 中国图象图形学报, 2024, 29 (6): 1479- 1509.
	WANG M , HUANG Z Z , HE H G , et al. Potential and prospects of segment anything model: a survey. Journal of Image and Graphics, 2024, 29 (6): 1479- 1509.
16	孙兴, 蔡肖红, 李明, 等. 视觉大模型SAM在医学图像分割中的应用综述. 计算机工程与应用, 2024, 60 (17): 1- 16.
	SUN X , CAI X H , LI M , et al. Review of application of visual foundation model SAM in medical image segmentation. Computer Engineering and Applications, 2024, 60 (17): 1- 16.
17	ALI M , WU T , HU H J , et al. A review of the Segment Anything Model (SAM) for medical image analysis: accomplishments and perspectives. Computerized Medical Imaging and Graphics, 2025, 119, 102473. doi: 10.1016/j.compmedimag.2024.102473
18	DOSOVITSKIY A. An image is worth 16×16 words: Transformers for image recognition at scale[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2010.11929.
19	RONNEBERGER O , FISCHER P , BROX T . U-Net: convolutional networks for biomedical image segmentation. Berlin, Germany: Springer International Publishing, 2015.
20	CHEN L C, PAPANDREOU G, SCHROFF F, et al. Rethinking atrous convolution for semantic image segmentation[EB/OL]. [2024-10-11]. https://arxiv.org/abs/1706.05587v3.
21	HE K M, CHEN X L, XIE S N, et al. Masked autoencoders are scalable vision learners[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2022: 15979-15988.
22	ZHAO X, DING W C, AN Y Q, et al. Fast segment anything[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2306.12156v1.
23	ZHANG C N, HAN D S, QIAO Y, et al. Faster segment anything: towards lightweight SAM for mobile applications[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2306.14289v2.
24	ZHANG C N, HAN D S, ZHENG S, et al. MobileSAMv2: faster segment anything to everything[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2312.09579v1.
25	XIONG Y Y, VARADARAJAN B, WU L M, et al. EfficientSAM: leveraged masked image pretraining for efficient segment anything[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2024: 16111-16121.
26	ZHANG Z Y, CAI H, HAN S. EfficientViT-SAM: accelerated segment anything model without performance loss[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Washington D.C., USA: IEEE Press, 2024: 7859-7863.
27	ZHOU C, LI X T, LOY C C, et al. EdgeSAM: prompt-in-the-loop distillation for on-device deployment of SAM[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2312.06660v2.
28	KE L, YE M, DANELLJAN M, et al. Segment anything in high quality[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2306.01567.
29	SONG Y, ZHOU Q, LI X, et al. BA-SAM: scalable bias-mode attention mask for segment anything model[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D.C., USA: IEEE Press, 2024: 3162-3173.
30	LI F, ZHANG H, SUN P Z, et al. Semantic-SAM: segment and recognize anything at any granularity[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2307.04767v1.
31	FENG Z S , ZHANG Y L , CHEN Y H , et al. SwinSAM: fine-grained polyp segmentation in colonoscopy images via segment anything model integrated with a Swin Transformer decoder. Biomedical Signal Processing and Control, 2025, 100, 107055. doi: 10.1016/j.bspc.2024.107055
32	CHEN W T, VONG Y J, KUO S Y, et al. RobustSAM: segment anything robustly on degraded images[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2406.09627v1.
33	ZHANG L, LIANG Y, ZHANG R, et al. BLO-SAM: bi-level optimization based finetuning of the segment anything model for overfitting-preventing semantic segmentation[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2402.16338.
34	JIANG M Z, ZHOU J Y, WU J D, et al. Uncertainty-Aware Adapter: adapting Segment Anything Model (SAM) for ambiguous medical image segmentation[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2403.10931v2.
35	WU J D, JI W, LIU Y P, et al. Medical SAM adapter: adapting segment anything model for medical image segmentation[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2304.12620v7.
36	MA J , HE Y , LI F , et al. Segment anything in medical images. Nature Communications, 2024, 15 (1): 654. doi: 10.1038/s41467-024-44824-z
37	ZHANG K D, LIU D. Customized segment anything model for medical image segmentation[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2304.13785v2.
38	GAO Y F, XIA W, HU D D, et al. DeSAM: decoupled segment anything model for generalizable medical image segmentation[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2306.00499v2.
39	CHEN T R, ZHU L Y, DING C T, et al. SAM-Adapter: adapting segment anything in underperformed scenes[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). Washington D.C., USA: IEEE Press, 2023: 3359-3367.
40	HUANG Y, LAI W B, JI J Y, et al. HRSAM: efficient interactive segmentation in high-resolution images[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2407.02109v2.
41	LI B, XIAO H K, TANG L. ASAM: boosting segment anything model with adversarial tuning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2024: 3699-3710.
42	胡升龙, 陈彬, 张开华, 等. 场景结构知识增强的协同显著性目标检测. 计算机工程, 2025, 51 (1): 31- 41. doi: 10.19678/j.issn.1000-3428.0070064
	HU S L , CHEN B , ZHANG K H , et al. Co-saliency object detection enhanced by scene structure knowledge. Computer Engineering, 2025, 51 (1): 31- 41. doi: 10.19678/j.issn.1000-3428.0070064
43	CHEN K Y , LIU C Y , CHEN H , et al. RSPrompter: learning to prompt for remote sensing instance segmentation based on visual foundation model. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62, 4701117.
44	YUE W X, ZHANG J, HU K, et al. SurgicalSAM: efficient class promptable surgical instrument segmentation[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2024: 6890-6898.
45	SUN Y P, CHEN J H, ZHANG S, et al. VRP-SAM: SAM with visual reference prompt[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2024: 23565-23574.
46	MO S T, TIAN Y P. AV-SAM: segment anything model meets audio-visual localization and segmentation[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2305.01836v1.
47	ZHANG Y X, CHENG T H, ZHU L H, et al. EVF-SAM: early vision-language fusion for text-prompted segment anything model[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2406.20076v5.
48	RAJI ACˇG F, KE L, TAI Y W, et al. Segment anything meets point tracking[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2307.01197v2.
49	CHEN P F, XIE L X, HUO X Y, et al. SAM-CP: marrying SAM with composable prompts for versatile segmentation[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2407.16682v1.
50	ZHANG R R, JIANG Z K, GUO Z Y, et al. Personalize segment anything model with one shot[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2305.03048v2.
51	ZHOU C P, NING K J, SHEN Q Q, et al. SAM-SP: self-prompting makes SAM great again[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2408.12364v1.
52	XU Y S, TANG J Q, MEN A D, et al. EviPrompt: a training-free evidential prompt generation method for segment anything model in medical images[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2311.06400v1.
53	CHEN Z, XU Q, LIU X Y, et al. UN-SAM: universal prompt-free segmentation for generalized nuclei images[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2402.16663v1.
54	白宇, 王珺, 冉红雷, 等. 半导体器件内部缺陷标注与检测方法研究. 计算机工程, 2024, 50 (12): 245- 253. doi: 10.19678/j.issn.1000-3428.0068712
	BAI Y , WANG J , RAN H L , et al. Research on internal defect annotation and detection methods of semiconductor devices. Computer Engineering, 2024, 50 (12): 245- 253. doi: 10.19678/j.issn.1000-3428.0068712
55	LENG T A, ZHANG Y M, HAN K, et al. Self-sampling meta SAM: enhancing few-shot medical image segmentation with meta-learning[C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). Washington D.C., USA: IEEE Press, 2024: 7910-7920.
56	QI X Y , WU Y F , MAO Y Q , et al. Self-guided few-shot semantic segmentation for remote sensing imagery based on large vision models. Berlin, Germany: Springer, 2024.
57	HE C, LI K, ZHANG Y, et al. Weakly-supervised concealed object segmentation with sam-based pseudo labeling and multi-scale feature grouping[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2305.11003.
58	HU M Z, LI Y H, YANG X F. SkinSAM: empowering skin cancer segmentation with segment anything model[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2304.13973v1.
59	CAO Y K, XU X H, SUN C, et al. Segment any anomaly without training via hybrid prompt regularization[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2305.10724v1.
60	CUI C , DENG R N , LIU Q , et al. All-in-SAM: from weak annotation to pixel-wise nuclei segmentation with prompt-based finetuning. Journal of Physics: Conference Series, 2024, 2722 (1): 012012. doi: 10.1088/1742-6596/2722/1/012012
61	DAI H X, MA C, YAN Z L, et al. SAMAug: point prompt augmentation for segment anything model[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2307.01187v4.
62	WU K , ZHANG J N , PENG H W , et al. TinyViT: fast pretraining distillation for small vision transformers. Berlin, Germany: Springer, 2022.
63	ZHANG H J, SU Y Y, XU X, et al. Improving the generalization of segmentation foundation model under distribution shift via weakly supervised adaptation[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2024: 23385-23395.
64	SAHOO P, SINGH A K, SAHA S, et al. A systematic survey of prompt engineering in large language models: techniques and applications[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2402.07927v2.
65	ANTONIOU A, EDWARDS H, STORKEY A. How to train your MAML[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2402.16338.
66	SUN W X, LIU Z Y, ZHANG Y H, et al. An alternative to WSSS? An empirical study of the Segment Anything Model (SAM) on weakly-supervised semantic segmentation problems[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2305.01586v2.
67	HO J, JAIN A, ABBEEL P. Denoising diffusion probabilistic models[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2006.11239.
68	XU Q, LI J X, HE X J, et al. ESP-MedSAM: efficient self-prompting SAM for universal domain-generalized medical image segmentation[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2407.14153v4.
69	YILDIZ Z, GU H, ZHANG J, et al. SegmentWithSAM: 3D slicer extension for Segment Anything Model (SAM)[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2408.15224.
70	WANG D, ZHANG J, DU B, et al. SAMRS: scaling-up remote sensing segmentation dataset with segment anything model[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2305.02034.
71	方乐缘, 旷洋, 刘强, 等. 基于时差提示SAM的遥感变化检测. 信号处理, 2024, 40 (3): 417- 427.
	FANG L Y , KUANG Y , LIU Q , et al. Temporal difference prompted SAM for remote sensing change detection. Journal of Signal Processing, 2024, 40 (3): 417- 427.
72	ZHANG J, YANG X B, JIANG R, et al. RSAM-Seg: a SAM-based approach with prior knowledge integration for remote sensing image semantic segmentation[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2402.19004v1.
73	LEE H , KIM K , LEE K . Application of Geo-Segment Anything Model (SAM) scheme to water body segmentation: an experiment study using CAS500-1 images. Korean Journal of Remote Sensing, 2024, 40 (4): 343- 350.
74	ZHANG X, LIU Y, LIN Y M, et al. UV-SAM: adapting segment anything model for urban village identification[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2024: 22520-22528.
75	XI L D , YU J C , GE D Q , et al. SAM-CFFNet: SAM-based cross-feature fusion network for intelligent identification of landslides. Remote Sensing, 2024, 16 (13): 2334. doi: 10.3390/rs16132334
76	GIANNAKIS I, BHARDWAJ A, SAM L, et al. Deep learning universal crater detection using Segment Anything Model (SAM)[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2304.07764v1.
77	ZHANG S M, LU Q H. Innovative integration of visual foundation model with a robotic arm on a mobile platform[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2404.18720v1.
78	MOENCK K, WENDT A, PRVNTE P, et al. Industrial segment anything—a case study in aircraft manufacturing, intralogistics, maintenance, repair, and overhaul[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2307.12674v1.
79	LIANG W, MA X G. Group-Mix SAM: lightweight solution for industrial assembly line applications[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2403.10053v1.
80	LI Z S, HUO D, MEURER M, et al. Efficient cutting tool wear segmentation based on segment anything model[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2407.01211.
81	YANG Y H, WU X Y, HE T, et al. SAM3D: segment anything in 3D scenes[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2306.03908v1.
82	CORDTS M, OMRAN M, RAMOS S, et al. The Cityscapes dataset for semantic urban scene understanding[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C., USA: IEEE Press, 2016: 3213-3223.
83	NEUHOLD G, OLLMANN T, BULÒ S R, et al. The Mapillary Vistas dataset for semantic understanding of street scenes[C]// Proceedings of the IEEE International Conference on Computer Vision (ICCV). Washington D. C., USA: IEEE Press, 2017: 5000-5009.
84	LAKHANI P , MONGAN J , SINGHAL C , et al. The 2021 SIIM-FISABIO-RSNA machine learning COVID-19 challenge: annotation and standard exam classification of COVID-19 chest radiographs. Journal of Digital Imaging, 2023, 36 (1): 365- 372.
85	LIN T Y , MAIRE M , BELONGIE S , et al. Microsoft COCO: common objects in context. Berlin, Germany: Springer, 2014.
86	EVERINGHAM M , VAN GOOL L , WILLIAMS C K I , et al. The PASCAL Visual Object Classes (VOC) challenge. International Journal of Computer Vision, 2010, 88 (2): 303- 338. doi: 10.1007/s11263-009-0275-4
87	ZHOU B L , ZHAO H , PUIG X , et al. Semantic understanding of scenes through the ADE20K dataset. International Journal of Computer Vision, 2019, 127 (3): 302- 321. doi: 10.1007/s11263-018-1140-0
88	MARTIN D, FOWLKES C, TAL D, et al. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics[C]//Proceedings of the 8th IEEE International Conference on Computer Vision. Washington D. C., USA: IEEE Press, 2001: 416-423.
89	DENG J, DONG W, SOCHER R, et al. ImageNet: a large-scale hierarchical image database[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2009: 248-255.
90	WANG L J, LU H C, WANG Y F, et al. Learning to detect salient objects with image-level supervision[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C., USA: IEEE Press, 2017: 3796-3805.
91	WANG J J, ZHENG Z, MA A L, et al. LoveDA: a remote sensing land-cover dataset for domain adaptive semantic segmentation[EB/OL]. [2024-10-11]. https://arxiv.org/abs/2110.08733v6.
92	LECLERC S , SMISTAD E , PEDROSA J , et al. Deep learning for segmentation using an open large-scale dataset in 2D echocardiography. IEEE Transactions on Medical Imaging, 2019, 38 (9): 2198- 2210. doi: 10.1109/TMI.2019.2900516
93	ZHANG J, FAN D P, DAI Y C, et al. RGB-D saliency detection via cascaded mutual information minimization[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Washington D. C., USA: IEEE Press, 2021: 4318-4327.
94	TU Z Z , XIA T , LI C L , et al. RGB-T image saliency detection via collaborative graph learning. IEEE Transactions on Multimedia, 2020, 22 (1): 160- 173. doi: 10.1109/TMM.2019.2924578
95	QIN X B , DAI H , HU X B , et al. Highly accurate dichotomous image segmentation. Berlin, Germany: Springer, 2022.
96	FAN D P, JI G P, SUN G L, et al. Camouflaged object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C., USA: IEEE Press, 2020: 2777-2787.
97	VICENTE T F Y , HOU L , YU C P , et al. Large-scale training of shadow detectors with noisily-annotated shadow examples. Berlin, Germany: Springer International Publishing, 2016.
98	FAN D P , JI G P , XU P , et al. Advances in deep concealed scene understanding. Visual Intelligence, 2023, 1 (1): 16. doi: 10.1007/s44267-023-00019-6
99	TAJBAKHSH N , GURUDU S R , LIANG J M . Automated polyp detection in colonoscopy videos using shape and context information. IEEE Transactions on Medical Imaging, 2016, 35 (2): 630- 644. doi: 10.1109/TMI.2015.2487997
100	SHUMAILOV I , SHUMAYLOV Z , ZHAO Y R , et al. AI models collapse when trained on recursively generated data. Nature, 2024, 631 (8022): 755- 759. doi: 10.1038/s41586-024-07566-y

[1]	郝宏达, 罗健旭. 基于多尺度区域特征融合的多器官语义分割模型[J]. 计算机工程, 2025, 51(8): 270-280.
[2]	李白芽. 基于CNN-Transformer的电子喉镜病灶及器官分割网络[J]. 计算机工程, 2025, 51(6): 327-337.
[3]	刘兆伟, 方艳红, 郑明宇, 锁斌. 基于注意力机制与多任务的肺部疾病诊断方法[J]. 计算机工程, 2025, 51(1): 332-342.
[4]	胡升龙, 陈彬, 张开华, 宋慧慧. 场景结构知识增强的协同显著性目标检测[J]. 计算机工程, 2025, 51(1): 31-41.
[5]	郭敏, 张熙涵, 李阳. 融合注意力的教师互一致性半监督医学图像分割[J]. 计算机工程, 2024, 50(9): 313-323.
[6]	高爽, 史轶伦, 徐巧枝, 于磊. 基于对比学习的非对称编解码结构的心脏MRI分割研究[J]. 计算机工程, 2024, 50(8): 290-300.
[7]	胡帅, 李华玲, 郝德琛. 改进U-Net的多级边缘增强医学图像分割网络[J]. 计算机工程, 2024, 50(4): 286-293.
[8]	姜百浩, 刘静, 仇大伟, 姜良. 深度学习在脊柱图像分割中的应用综述[J]. 计算机工程, 2024, 50(3): 1-15.
[9]	傅杨淦, 朱岚巍, 吴虹蓉, 陈方. 基于改进U-Net的珊瑚礁底栖物质信息提取方法[J]. 计算机工程, 2023, 49(12): 231-242.
[10]	杨本臣, 贾宇航, 金海波. 融合多分支特征的肝脏和肝脏肿瘤的体积分割[J]. 计算机工程, 2023, 49(10): 194-201.
[11]	褚张晴晴, 钟志强, 颜子夜, 战荫伟. 基于特征融合与注意力机制的脑肿瘤分割算法[J]. 计算机工程, 2023, 49(10): 154-161.
[12]	乔彩彩, 吴成茂, 李昌兴, 王佳烨. 结合隶属度与像素交替引导滤波的鲁棒模糊聚类算法[J]. 计算机工程, 2022, 48(8): 224-233.
[13]	林志洁, 郑秋岚, 梁涌, 邢卫. 基于内卷U-Net的医学图像分割模型[J]. 计算机工程, 2022, 48(8): 180-186.
[14]	黄胜, 冉浩杉. 基于语义信息的精细化边缘检测方法[J]. 计算机工程, 2022, 48(3): 204-210.
[15]	张相芬, 刘艳, 袁非牛. 基于倒金字塔深度学习网络的三维医学图像分割[J]. 计算机工程, 2022, 48(12): 304-311.

选择文件类型/文献管理软件名称

选择包含的内容