CoChat
Sign Up
Cited by 767Advanced Neural Network ApplicationsDomain Adaptation and Few-Shot LearningVisual Attention and Saliency Detection

CenterMask: Real-Time Anchor-Free Instance Segmentation

Open access
Lee, Youngwan, Park, Jongyoul·2020·2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
DOI 10.1109/cvpr42600.2020.01392
Open this paper in CoChat — free accountOpen PDF

Abstract

We propose a simple yet efficient anchor-free instance segmentation, called CenterMask, that adds a novel spatial attention-guided mask (SAG-Mask) branch to anchor-free one stage object detector (FCOS) in the same vein with Mask R-CNN. Plugged into the FCOS object detector, the SAG-Mask branch predicts a segmentation mask on each box with the spatial attention map that helps to focus on informative pixels and suppress noise. We also present an improved backbone networks, VoVNetV2, with two effective strategies: (1) residual connection for alleviating the optimization problem of larger VoVNet \cite{lee2019energy} and (2) effective Squeeze-Excitation (eSE) dealing with the channel information loss problem of original SE. With SAG-Mask and VoVNetV2, we deign CenterMask and CenterMask-Lite that are targeted to large and small models, respectively. Using the same ResNet-101-FPN backbone, CenterMask achieves 38.3%, surpassing all previous state-of-the-art methods while at a much faster speed. CenterMask-Lite also outperforms the state-of-the-art by large margins at over 35fps on Titan Xp. We hope that CenterMask and VoVNetV2 can serve as a solid baseline of real-time instance segmentation and backbone network for various vision tasks, respectively. The Code is available at https://github.com/youngwanLEE/CenterMask.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr42600.2020.01392

Cites

9 of 9 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • The Cellpose models outperform the LiveCell model released with the LiveCell dataset.

    “The Cellpose models also outperform the LiveCell model released with the LiveCell dataset31.”

    From Cellpose 2.0: how to train your own model (2022) · cites this paper as [31]

    The Introduction and §3.2 compare CenterMask with other instance-segmentation methods on COCO, not Cellpose with a LiveCell model. Searches for Cellpose, LiveCell, and cell-segmentation comparisons found no passage in our copy addressing the claimed result. (LLM, conf=0.76)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 29

  1. Daniel Bolya, Chong Zhou, Fanyi Xiao, and Yong Jae Lee. Yolact: Real-time instance segmentation. In ICCV, 2019. 1, 2, 7, 8
  2. Kai Chen, Jiangmiao Pang, Jiaqi Wang, Yu Xiong, Xiaox- iao Li, Shuyang Sun, Wansen Feng, Ziwei Liu, Jianping Shi, Wanli Ouyang, et al. Hybrid task cascade for instance seg- mentation. In CVPR, pages 4974-4983, 2019. 1, 8
  3. Long Chen, Hanwang Zhang, Jun Xiao, Liqiang Nie, Jian Shao, Wei Liu, and Tat-Seng Chua. Sca-cnn: Spatial and channel-wise attention in convolutional networks for image captioning. In CVPR, pages 5659-5667, 2017. 3
  4. Xinlei Chen, Ross Girshick, Kaiming He, and Piotr Dollar. Tensormask: A foundation for dense object segmentation. In ICCV, 2019. 7, 8
  5. Kaiwen Duan, Song Bai, Lingxi Xie, Honggang Qi, Qing- ming Huang, and Qi Tian. Centernet: Keypoint triplets for object detection. In ICCV, 2019. 2
  6. Cheng-Yang Fu, Mykhailo Shvets, and Alexander C Berg. Retinamask: Learning to predict masks improves state- of-the-art single-shot detection for free. arXiv preprint arXiv:1901.03353, 2019. 7, 8 · arXiv
  7. Kaiming He, Ross Girshick, and Piotr Dollar. Rethinking imagenet pre-training. In ICCV, 2019. 7
  8. Kaiming He, Georgia Gkioxari, Piotr Dollár, and Ross Gir- shick. Mask r-cnn. In ICCV, 2017. 1, 2, 3, 5, 6, 8
  9. Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco An- dreetto, and Hartwig Adam. Mobilenets: Efficient convolu- tional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861, 2017. 2 · arXiv
  10. Jie Hu, Li Shen, Samuel Albanie, Gang Sun, and Andrea Vedaldi. Gather-excite: Exploiting feature context in convo- lutional neural networks. In NIPS, pages 9401-9411, 2018.
  11. Jie Hu, Li Shen, and Gang Sun. Squeeze-and-excitation net- works. In CVPR, pages 7132-7141, 2018. 2, 3, 4, 7
  12. Gao Huang, Zhuang Liu, Laurens Van Der Maaten, and Kil- ian Q Weinberger. Densely connected convolutional net- works. In CVPR, 2017. 2
  13. Zhaojin Huang, Lichao Huang, Yongchao Gong, Chang Huang, and Xinggang Wang. Mask scoring r-cnn. In CVPR, pages 6409-6418, 2019. 1, 5, 6
  14. Weicheng Kuo, Anelia Angelova, Jitendra Malik, and Tsung-Yi Lin. Shapemask: Learning to segment novel ob- jects by refining shape priors. In ICCV, 2019. 8
  15. Hei Law and Jia Deng. Cornernet: Detecting objects as paired keypoints. In ECCV, pages 734-750, 2018. 2
  16. Youngwan Lee, Joong-won Hwang, Sangrok Lee, Yuseok Bae, and Jongyoul Park. An energy and gpu-computation efficient backbone network for real-time object detection. In CVPR Workshops, pages 0-0, 2019. 1, 2, 4, 7
  17. Yanghao Li, Yuntao Chen, Naiyan Wang, and Zhaoxiang Zhang. Scale-aware trident networks for object detection. arXiv preprint arXiv:1901.01892, 2019. 1 · arXiv
  18. Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick. Microsoft coco: Common objects in context. In ECCV, 2014. 1, 2, 5
  19. Shu Liu, Lu Qi, Haifang Qin, Jianping Shi, and Jiaya Jia. Path aggregation network for instance segmentation. In CVPR, pages 8759-8768, 2018. 1
  20. Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C Berg. Ssd: Single shot multibox detector. In ECCV, 2016. 7
  21. Jonathan Long, Evan Shelhamer, and Trevor Darrell. Fully convolutional networks for semantic segmentation. In CVPR, pages 3431-3440, 2015. 3
  22. Zheng Qin, Zeming Li, Zhaoning Zhang, Yiping Bao, Gang Yu, Yuxing Peng, and Jian Sun. Thundernet: Towards real- time generic object detection on mobile devices. In ICCV, 2019. 3
  23. Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zh- moginov, and Liang-Chieh Chen. Mobilenetv2: Inverted residuals and linear bottlenecks. In CVPR, pages 4510-4520, 2018. 7
  24. Ke Sun, Yang Zhao, Borui Jiang, Tianheng Cheng, Bin Xiao, Dong Liu, Yadong Mu, Xinggang Wang, Wenyu Liu, and Jingdong Wang. High-resolution representations for labeling pixels and regions. arXiv preprint arXiv:1904.04514, 2019. 2, 7 · arXiv
  25. Sanghyun Woo, Jongchan Park, Joon-Young Lee, and In So Kweon. Cbam: Convolutional block attention module. In ECCV, pages 3-19, 2018. 3
  26. Saining Xie, Ross Girshick, Piotr Dollár, Zhuowen Tu, and Kaiming He. Aggregated residual transformations for deep neural networks. In CVPR, 2017. 2, 7
  27. Kimin Yun, Yongjin Kwon, Sungchan Oh, Jinyoung Moon, and Jongyoul Park. Vision-based garbage dumping action detection for real-world surveillance platform. ETRI Journal, 41(4):494-505, 2019. 8
  28. Xingyi Zhou, Dequan Wang, and Philipp Krähenbühl. Ob- jects as points. In arXiv preprint arXiv:1904.07850, 2019. · arXiv
  29. Xizhou Zhu, Dazhi Cheng, Zheng Zhang, Stephen Lin, and Jifeng Dai. An empirical study of spatial attention mecha- nisms in deep networks. In ICCV, 2019. 3

Cited by

Sorted by citations

Authors
Lee, Y., & Park, J.
Affiliations
Electronics and Telecommunications Research Institute (KR)
ORCID
Venue
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2020-06
Pages
13903-13912
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr42600.2020.01392
OpenAlex
W2987206775
Cited by
767
References
9
Citations by year
2026: 58 · 2025: 123 · 2024: 151 · 2023: 157 · 2022: 130 · 2021: 114 · 2020: 32 · 2019: 1
FWCI
33.39
Type
conference paper
Language
en
Open access
Licence
Locations
  • IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • Electronics and Telecommunications Research Institute
  • Ministry of Science and ICT, South Korea (B0101-15-0266, 2020-0-00004)
  • Institute for Information and Communications Technology Promotion (B0101-15-0266, 2020-0-00004)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
Keywords
instance segmentation, anchor-free detection, FCOS, spatial attention, real-time segmentation, squeeze-and-excitation, lightweight models

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review