Interactive Object Segmentation With Inside-Outside Guidance
Abstract
This paper explores how to harvest precise object segmentation masks while minimizing the human interaction cost. To achieve this, we propose an Inside-Outside Guidance (IOG) approach in this work. Concretely, we leverage an inside point that is clicked near the object center and two outside points at the symmetrical corner locations (top-left and bottom-right or top-right and bottom-left) of a tight bounding box that encloses the target object. This results in a total of one foreground click and four background clicks for segmentation. The advantages of our IOG is four-fold: 1) the two outside points can help to remove distractions from other objects or background; 2) the inside point can help to eliminate the unrelated regions inside the bounding box; 3) the inside and outside points are easily identified, reducing the confusion raised by the state-of-the-art DEXTR in labeling some extreme samples; 4) our approach naturally supports additional clicks annotations for further correction. Despite its simplicity, our IOG not only achieves state-of-the-art performance on several popular benchmarks, but also demonstrates strong generalization capability across different domains such as street scenes, aerial imagery and medical images, without fine-tuning. In addition, we also propose a simple two-stage solution that enables our IOG to produce high quality instance segmentation masks from existing datasets with off-the-shelf bounding boxes such as ImageNet and Open Images, demonstrating the superiority of our IOG as an annotation tool.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
In IOG training, the position of the object center is simulated as the inside point.
“According to IOG algorithm, the position of the object center is simulated as the inside point during training.”
From Automatic Inside Point Localization with Deep Reinforcement Learning for Interactive Object Segmentation (2021) · cites this paper as [16]
Inconsistent inputs between training and testing when annotating the inside point often have a negative effect on segmentation performance.
“As discussed in [16], the inconsistent inputs between training and testing when annotating the inside point will often have a negative effect on the segmentation performance.”
From Automatic Inside Point Localization with Deep Reinforcement Learning for Interactive Object Segmentation (2021) · cites this paper as [16]
The IOG algorithm chooses the point whose ε(p)=1 in cropped images as the simulated inside point.
“The IOG algorithm chooses the point whose ε(p)=1 in cropped images as the simulated inside point.”
From Automatic Inside Point Localization with Deep Reinforcement Learning for Interactive Object Segmentation (2021) · cites this paper as [16]
The Inside-Outside Guidance (IOG) algorithm requires three points: one inside point located around the center of the object and two outside points at symmetrical corner locations that form an almost-tight bounding box enclosing the target object.
“In an IOG algorithm, the workload of the annotator is reduced to only providing three points: an inside point located around the center of the object and two outside points at any symmetrical corner locations that form an almost-tight bounding box enclosing the target object of interest.”
From Automatic Inside Point Localization with Deep Reinforcement Learning for Interactive Object Segmentation (2021) · cites this paper as [16]
The Inside-Outside Guidance (IOG) algorithm achieves fast clicking speed and excellent segmentation results across different application domains.
“Despite its simplicity, the Inside-Outside Guidance (IOG) algorithm has shown fast clicking speed and excellent segmentation results across different application domains.”
From Automatic Inside Point Localization with Deep Reinforcement Learning for Interactive Object Segmentation (2021) · cites this paper as [16]
IPL-Net outperforms the outside only and two-stage methods by more than 0.8% and 0.6% IoU accuracy on PASCAL val using outside points annotations only.
“It can be observed that our IPL-Net outperforms the other two algorithm by more than 0.8% and 0.6%, which well validate the effectiveness of our proposed method in inferring the position of the inside point to help the IOG algorithm to achieve accurate performance.”
From Automatic Inside Point Localization with Deep Reinforcement Learning for Interactive Object Segmentation (2021) · cites this paper as [16]
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
Feature Pyramid Networks for Object Detection
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.106 · Cited by 30,939 · see citing works
CCNet: Criss-Cross Attention for Semantic Segmentation
Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., & Liu, W. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00069 · Cited by 3,045 · see citing works
Self-citationThe Mapillary Vistas Dataset for Semantic Understanding of Street Scenes
Neuhold, G., Ollmann, T., Bulo, S. R., & Kontschieder, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.534 · Cited by 1,434 · see citing works
The Cityscapes Dataset for Semantic Urban Scene Understanding
Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016) · arXiv · doi:10.48550/arxiv.1604.01685 · Cited by 1,174 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
3DSAM-adapter: Holistic adaptation of SAM from 2D to 3D for promptable tumor segmentation
Gong, S., Zhong, Y., Ma, W., Li, J., Wang, Z., Zhang, J., Heng, P.-A., & Dou, Q. (2024) · Medical Image Analysis · doi:10.1016/j.media.2024.103324 · Cited by 156 · see citing works
Volumetric memory network for interactive medical image segmentation
Zhou, T., Li, L., Bredell, G., Li, J., Unkelbach, J., & Konukoglu, E. (2023) · Medical Image Analysis · doi:10.1016/j.media.2022.102599 · Cited by 109 · see citing works
Aresta, G., Araújo, T., Fazekas, B., Mai, J., Schmidt-Erfurth, U., & Bogunović, H. (2024) · IEEE Access · doi:10.1109/access.2024.3379015 · Cited by 5 · see citing works
“In both approaches, the user input is commonly encoded as an attention map, which can then be used as a feature map and/or a weighting term for the training loss [21], [22], [23], [24].”
MethodTian, Z., He, Y., Sun, L., Li, Y., & Du, S. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128184 · Cited by 5 · see citing works
Li, G., Zhang, G., & Qin, C. (2021) · Sensors · doi:10.3390/s21186100 · Cited by 2 · see citing works
“(a) IOG [16] segmentation example with different inside points.”
BackgroundMethodInfluential
- Authors
- Zhang, S., Liew, J. H., Wei, Y., Wei, S., & Zhao, Y.
- Affiliations
- Beijing Jiaotong University (CN)
- National University of Singapore (SG)
- University of Technology Sydney (AU)
- Venue
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2020-06
- Pages
- 12231-12241
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3034586976
- Cited by
- 142
- References
- 5
- Citations by year
- 2026: 12 · 2025: 20 · 2024: 30 · 2023: 31 · 2022: 32 · 2021: 16 · 2020: 1
- FWCI
- 6.17
- Type
- conference paper
- Language
- en
- Open access
- closed
- 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)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- click-based segmentation, instance segmentation masks, bounding box annotation, interactive segmentation, annotation tools, two-stage segmentation, medical image segmentation
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
