Anchor-free instance segmentation algorithm based on YOLACTR

Mei Ting; Zhao Jingwei; Lin Shanling; Xie Ziyu; Lin Zhixian; Guo Tailiang

doi:10.12086/oee.2025.240265

Article navigation > Opto-Electronic Engineering > 2025 Vol. 52 > No. 5 > 240265

Next Article Previous Article

Mei T, Zhao J W, Lin S L, et al. Anchor-free instance segmentation algorithm based on YOLACTR[J]. Opto-Electron Eng, 2025, 52(5): 240265. doi: 10.12086/oee.2025.240265

Citation:

Mei T, Zhao J W, Lin S L, et al. Anchor-free instance segmentation algorithm based on YOLACTR[J]. Opto-Electron Eng, 2025, 52(5): 240265. doi: 10.12086/oee.2025.240265

Anchor-free instance segmentation algorithm based on YOLACTR

1.
College of Physics and Information Engineering, Fuzhou University, Fuzhou, Fujian 350116, China
2.
Fujian Science & Technology Innovation Laboratory for Optoelectronic Information of China, Fuzhou, Fujian 350108, China
3.
School of Advanced Manufacturing, Fuzhou University, Quanzhou, Fujian 362200, China

Fund Project: National Key Research and Development Program (2021YFB3600603), National Youth Science Foundation (62101132)

More Information

^*Corresponding author: 526176333@qq.com
CSTR: 32245.14.oee.2025.240265

Received Date 12 November 2024

Revised Date 07 April 2025

Accepted Date 08 April 2025

Published Date 30 May 2025

Abstract

Abstract

Aiming at the problem that the single-stage YOLACT algorithm based on bounding box detection lacks the location and extraction of the region of interest, and the issue that two bounding boxes overlap and are difficult to distinguish, this paper proposes an anchor-free instance segmentation method based on the improved YOLACTR algorithm. The mask generation is decoupled into feature learning and convolution kernel learning, and the feature aggregation network is used to generate mask features. By adding position information to the feature map, multi-layer transformer and two-way attention are used to obtain dynamic convolution kernels. The experimental results show that this method achieves a mask accuracy (AP) of 35.2% on the MS COCO public dataset. Compared with the YOLACT algorithm, this method improves the mask accuracy by 25.7%, the small target detection accuracy by 37.1%, the medium target detection accuracy by 25.8%, and the large target detection accuracy by 21.9%. Compared with YOLACT, Mask R-CNN, SOLO, and other methods, our algorithm shows significant advantages in segmentation accuracy and edge detail preservation, especially excelling in overlapping object segmentation and small target detection, effectively solving the problem of incorrect segmentation in instance boundary overlap regions that traditional methods face.
- YOLACT /
- anchor-free instance segmentation /
- dynamic convolution /
- Transformer

FullText(HTML)

References

[1]	周涛, 赵雅楠, 陆惠玲, 等. 医学图像实例分割:从有候选区域向无候选区域[J]. 生物医学工程学杂志, 2022, 39(6): 1218−1232 doi: 10.7507/1001-5515.202201034 CrossRef Google Scholar Zhou T, Zhao Y N, Lu H L, et al. Medical image instance segmentation: from candidate region to no candidate region[J]. J Biomed Eng, 2022, 39(6): 1218−1232. doi: 10.7507/1001-5515.202201034 CrossRef Google Scholar
[2]	Pei S W, Ni B, Shen T M, et al. RISAT: real-time instance segmentation with adversarial training[J]. Multimed Tools Appl, 2023, 82(3): 4063−4080. doi: 10.1007/s11042-022-13447-1 CrossRef Google Scholar
[3]	Hong S L, Jiang Z H, Liu L Z, et al. Improved mask R-CNN combined with Otsu preprocessing for rice panicle detection and segmentation[J]. Appl Sci, 2022, 12(22): 11701. doi: 10.3390/app122211701 CrossRef Google Scholar
[4]	吴马靖, 张永爱, 林珊玲, 等. 基于BiLevelNet的实时语义分割算法[J]. 光电工程, 2024, 51(5): 240030. doi: 10.12086/oee.2024.240030 CrossRef Google Scholar Wu M J, Zhang Y A, Lin S L, et al. Real-time semantic segmentation algorithm based on BiLevelNet[J]. Opto-Electron Eng, 2024, 51(5): 240030. doi: 10.12086/oee.2024.240030 CrossRef Google Scholar
[5]	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. doi: 10.11992/tis.202109043 CrossRef Google Scholar Su L, Sun Y X, Yuan S Z. A survey of instance segmentation research based on deep learning[J]. CAAI Trans Intell Syst, 2021, 17(1): 16−31. doi: 10.11992/tis.202109043 CrossRef Google Scholar
[6]	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. doi: 10.3969/j.issn.1000-1220.2021.01.028 CrossRef Google Scholar Zhang J K, Zhao J, Zhang R, et al. Survey of image instance segmentation methods using deep learning[J]. J Chin Comput Syst, 2021, 42(1): 161−171. doi: 10.3969/j.issn.1000-1220.2021.01.028 CrossRef Google Scholar
[7]	Minaee S, Boykov Y, Porikli F, et al. Image segmentation using deep learning: a survey[J]. IEEE Trans Pattern Anal Mach Intell, 2022, 44(7): 3523−3542. doi: 10.1109/TPAMI.2021.3059968 CrossRef Google Scholar
[8]	He K M, Gkioxari G, Dollár P, et al. Mask R-CNN[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision, 2017: 2980–2988. https://doi.org/10.1109/ICCV.2017.322. Google Scholar
[9]	Ren S Q, He K M, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C]//Proceedings of the 29th International Conference on Neural Information Processing Systems, 2015: 91–99. Google Scholar
[10]	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, 2018: 6154–6162. https://doi.org/10.1109/CVPR.2018.00644. Google Scholar
[11]	肖振久, 田昊, 张杰浩, 等. 融合动态特征增强的遥感建筑物分割[J]. 光电工程, 2020, 52(3): 240231 doi: 10.12086/oee.2025.240231 CrossRef Google Scholar Xiao Z J, Tian H, Zhang J H, et al. Fusion of dynamic features enhances remote sensing building segmentation[J]. Opto-Electron Eng, 2020, 52(3): 240231 doi: 10.12086/oee.2025.240231 CrossRef Google Scholar
[12]	Chen K, Pang J M, Wang J Q, et al. Hybrid task cascade for instance segmentation[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 4969–4978. https://doi.org/10.1109/CVPR.2019.00511. Google Scholar
[13]	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. https://doi.org/10.1109/CVPR.2016.91. Google Scholar
[14]	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, 2014: 580–587. https://doi.org/10.1109/CVPR.2014.81. Google Scholar
[15]	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, 2019: 9626–9635. https://doi.org/10.1109/ICCV.2019.00972. Google Scholar
[16]	Zhou X Y, Wang D Q, Krähenbühl P. Objects as points[Z]. arXiv: 1904.07850, 2019. https://arxiv.org/abs/1904.07850. Google Scholar
[17]	Wang X L, Kong T, Shen C H, et al. SOLO: segmenting objects by locations[C]//16th European Conference on Computer Vision, 2020: 649–665. https://doi.org/10.1007/978-3-030-58523-5_38. Google Scholar
[18]	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, 2016: 770–778. https://doi.org/10.1109/CVPR.2016.90. Google Scholar
[19]	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, 2017: 936–944. https://doi.org/10.1109/CVPR.2017.106. Google Scholar
[20]	刘腾, 刘宏哲, 李学伟, 等. 基于无锚框分割网络改进的实例分割方法[J]. 计算机工程, 2022, 48(9): 239−247,253. doi: 10.19678/j.issn.1000-3428.0062846 CrossRef Google Scholar Liu T, Liu H Z, Li X W, et al. Improved instance segmentation method based on anchor-free segmentation network[J]. Comput Eng, 2022, 48(9): 239−247,253. doi: 10.19678/j.issn.1000-3428.0062846 CrossRef Google Scholar
[21]	Kirillov A, Wu Y X, He K M, et al. PointRend: image segmentation as rendering[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 9796–9805. https://doi.org/10.1109/CVPR42600.2020.00982. Google Scholar
[22]	Yang S S, Wang X G, Li Y, et al. Temporally efficient vision transformer for video instance segmentation[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 2875–2885. https://doi.org/10.1109/CVPR52688.2022.00290. Google Scholar
[23]	Cheng B W, Misra I, Schwing A G, et al. Masked-attention mask transformer for universal image segmentation[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 1280–1289. https://doi.org/10.1109/CVPR52688.2022.00135. Google Scholar
[24]	Bolya D, Zhou C, Xiao F Y, et al. YOLACT: real-time instance segmentation[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019: 9156–9165. https://doi.org/10.1109/ICCV.2019.00925. Google Scholar
[25]	赵敬伟, 林珊玲, 梅婷, 等. 基于YOLACT与Transformer相结合的实例分割算法研究[J]. 半导体光电, 2023, 44(1): 134−140. doi: 10.16818/j.issn1001-5868.2022110201 CrossRef Google Scholar Zhao J W, Lin S L, Mei T, et al. Research on instance segmentation algorithm based on YOLACT and Transformer[J]. Semicond Optoelectron, 2023, 44(1): 134−140. doi: 10.16818/j.issn1001-5868.2022110201 CrossRef Google Scholar
[26]	Cordts M, Omran M, Ramos S, et al. The cityscapes dataset for semantic urban scene understanding[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016: 3213–3223. https://doi.org/10.1109/CVPR.2016.350. Google Scholar
[27]	Cordts M, Omran M, Ramos S, et al. The cityscapes dataset[C]//CVPR Workshop on the Future of Datasets in Vision, 2015: 1. https://doi.org/10.48550/arXiv.1604.01685 Google Scholar
[28]	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 Computer Vision and Pattern Recognition, 2020: 12190–12199. https://doi.org/10.1109/CVPR42600.2020.01221. Google Scholar

Overview

Overview

This paper proposes an anchor-free instance segmentation algorithm based on YOLACTR to address the limitations of the single-stage YOLACT algorithm in instance segmentation tasks. Traditional YOLACT algorithms rely on bounding box detection, suffering from precise localization of regions of interest and facing difficulties in distinguishing overlapping instances, which constrains detection accuracy. This research decouples the mask generation process into parallel tasks of feature learning and convolution kernel learning, abandoning traditional bounding box detection methods and adopting a more natural mask representation approach.

In the algorithmic implementation, random positional embedding techniques are employed to enhance the position sensitivity of feature maps, utilizing a six-layer Transformer structure to process spatial information, simultaneously generating dynamic convolution kernels and category information. The feature aggregation network integrates bottom-layer features from the feature pyramid and high-level features from the prediction network, optimizing feature expression capabilities through channel-spatial (CS) attention modules. For the loss function design, the research implements a combination of focal loss for classification tasks and dice loss for mask generation.

The network architecture consists of four primary components: a multi-scale feature generation network utilizing ResNet and feature pyramid networks; A mask generation network combining transformer with feature aggregation; A prediction network incorporating positional information to generate dynamic convolution kernels; Auxiliary network structures to enhance overall performance. This design allows for more effective handling of spatial relationships and instance boundaries compared to traditional anchor-based approaches.

Experimental results on the MS COCO dataset demonstrate that this method achieves a mask accuracy (AP) of 35.2%, representing a 25.7% improvement over the YOLACT algorithm. Specifically, the detection accuracy for small targets is improved by 37.1%, for medium targets by 25.8%, and for large target by 21.9%. When compared to algorithms such as Mask R-CNN, YOLACTR, and SOLO, this method shows advantages in segmentation accuracy and edge detail preservation. It performs exceptionally well in handling overlapping objects and small target detection, effectively addressing the segmentation issues in instance boundary overlap regions faced by traditional methods.

This paper effectively overcomes the limitations of traditional bounding box methods by decoupling the mask generation process and introducing anchor-free design, achieving balanced performance in instance segmentation tasks across different scales of objects, particularly improving small target detection capability and boundary differentiation of overlapping objects.