Segmentation by transduction

By Olivier Duchenne, Jean-Yves Audibert, Renaud Keriven, Jean Ponce, Florent Ségonne. 2008

134 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

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

In Computational Mechanics

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Extreme Clicking for Efficient Object Annotation (2017, methodology): “To reduce annotation time many interactive segmentation techniques have been proposed, which require the user to input either a bounding box around the object [42, 51, 71], or scribbles [3, 16, 24, 26, 27, 42, 50, 64, 65, 72], or clicks [31, 69].”
Geometry-Aware Learning of Maps for Camera Localization (2017, unknown): “This is a transductive learning scenario [9, 16].”
MILCut: A Sweeping Line Multiple Instance Learning Paradigm for Interactive Image Segmentation (2014, unknown): “Some representative works include geodesic approaches [28, 8], random walk approaches [39, 18], discriminative learning approaches [14, 43], and those methods using various kinds of priors [35, 15].”
Learning an interactive segmentation system (2009, unknown): “A fixed set of user-made interactions (brush strokes) associated with each image of the dataset is most commonly used in interactive image segmentation [6, 22, 8].”
Geodesic graph cut for interactive image segmentation (2010, methodology): “But, as also noted in [9], this is the only evaluation database to provide seeds, and we compute our results on this dataset for comparison (Table 1).”
Power Watershed: A Unifying Graph-Based Optimization Framework (2011, background): “Examination of the special cases of this general algorithm reveals a new class of watershed segmentation models.”
Nonparametric higher-order learning for interactive segmentation (2010, methodology): “The cost function defined as pairwise EX l,P and unary EX l,U terms is commonly used for segmentation [4][8].”
Geodesic star convexity for interactive image segmentation (2010, background): “Existing evaluation of interactive segmentation is either qualitative [2, 9] or is restricted to a fixed set of user interactions with seed points obtained by eroding and dilating the ground truth segmentation [1, 6].”
Y Qualification Main task Y Return N N Y User qualified ? N Feedback Pass ? Pass ? Annotator training Annotating images (2017, methodology): “To reduce annotation time many interactive segmentation techniques have been proposed, which require the user to input either a bounding box around the object [42, 51, 71], or scribbles [3, 16, 24, 26, 27, 42, 50, 64, 65, 72], or clicks [31, 69].”
User-Friendly Interactive Image Segmentation Through Unified Combinatorial User Inputs (2010, methodology): “Note that a simple adaptive threshold method was reported in [27] that can be combined with the existing algorithms such as the random walks to further reduce the error rate.”