SCALPEL: Segmentation Cascades with Localized Priors and Efficient Learning

By David J. Weiss, B. Taskar. 2013

26 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Pixelwise Instance Segmentation with a Dynamically Instantiated Network (2017, methodology): “In practice, we initialised these parameters with the shape priors described in [43].”
Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation (2015, background): “Weiss and Taskar [28] specialize the classiﬁers also to size and class of the annotated instances to produce object proposals.”
Multiscale Combinatorial Grouping (2014, background): “Weiss and Taskar [28] specialize the classifiers also to size and class of the annotated instances to produce object candidates.”
Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation (2017, background): “Weiss and Taskar [28] specialize the classifiers also to size and class of the annotated instances to produce object proposals.”
Multi-instance object segmentation with occlusion handling (2015, methodology): “Most recently, the SCALPEL [35] framework that integrates bottom-up cues and top-down priors such as object layout, class and scale into a cascade bottom-up segmentation scheme to generate object segments is proposed.”
Object proposal by multi-branch hierarchical segmentation (2015, methodology): “The method in [4, 3, 5] gives merge scores using global contour detection result; the methods in [12, 26, 23] heuristically define merging strategies based on appearance similarity and segment’s size; the methods in [24, 27] trains a cascade of linear classifiers and uses classifiers’ decision value”
Image Segmentation by Cascaded Region Agglomeration (2013, methodology): “However, SCALPEL relies heavily on class-specific shape priors for known object classes, and its objective is to produce a set of class-specific region proposals, that can be used in semantic image labeling.”
ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors (2019, methodology): “On the contrary, shapes are more informative (see right column) and have been used by numerous algorithms to help object segmentation [1, 47, 20, 7, 46].”
RIGOR: Reusing Inference in Graph Cuts for Generating Object Regions (2014, methodology): “Without supervision, systems such as [9, 6, 19, 34, 31] are able to generate a pool of overlapping segment proposals, where most foreground objects are captured by at least one segment from the pool.”