2013 IEEE International Conference on Computer Vision 2013
DOI: 10.1109/iccv.2013.271
|View full text |Cite
|
Sign up to set email alerts
|

Semantic Segmentation without Annotating Segments

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
46
0

Year Published

2014
2014
2023
2023

Publication Types

Select...
4
2
1

Relationship

1
6

Authors

Journals

citations
Cited by 42 publications
(46 citation statements)
references
References 17 publications
0
46
0
Order By: Relevance
“…Compared with histogram or GMM fitting used by [16], they argue that the fore/background regions can be clustered better using this energy. Probably the most similar work to us is Xia [6], which proposes to generate the object shape by directly selecting the best overlapping segments that align well to the object boundary and thereafter integrate it into the subsequent graph-cut based inference algorithm to obtain the segmentation results. Segmentation performance of this method heavily relies on the shape based graph-cut process.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…Compared with histogram or GMM fitting used by [16], they argue that the fore/background regions can be clustered better using this energy. Probably the most similar work to us is Xia [6], which proposes to generate the object shape by directly selecting the best overlapping segments that align well to the object boundary and thereafter integrate it into the subsequent graph-cut based inference algorithm to obtain the segmentation results. Segmentation performance of this method heavily relies on the shape based graph-cut process.…”
Section: Related Workmentioning
confidence: 99%
“…We utilize the generated object candidates as segment hypotheses bases. However, unlike [6], we operationalize this idea by exploring the usefulness of each segment towards object extraction based on an object reconstruction model. Furthermore, the pairwise correlation information of segment hypotheses can be preserved in our method, which is crucial to produce accurate and reliable results.…”
Section: Related Workmentioning
confidence: 99%
“…Methods of this category, e.g., [1,3,12,15,18,20,24,27,29], aim to identify objects of interest and segment them out at the same time. Owing to the high flexibility in modeling the dependencies among variables and observations, CRFs have been widely adopted in the task.…”
Section: Related Workmentioning
confidence: 99%
“…Recent research efforts have been made on reducing the labeling cost for object segmentation. Weakly supervised methods or cosegmentation, e.g., [13,18,29], support training data labeled in the levels of images or bounding boxes, instead of object maps. As information regarding object classes has been annotated, the class-specific clues were extracted in these methods to enhance object segmentation.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation