SLEDGE: Sequential Labeling of Image Edges for Boundary Detection

Payet, Nadia; Todorovic, Sinisa

doi:10.1007/s11263-013-0612-5

Cited by 19 publications

(13 citation statements)

References 68 publications

(122 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Search-based structure prediction methods are gaining momentum in computer vision [10,5,14,24], but they have never been used for scene labeling. Their key limitation is the requirement to approximate the loss function, and thus guide the search.…”

Section: Prior Work and Our Contributionsmentioning

confidence: 99%

Scene Labeling Using Beam Search under Mutex Constraints

Roy

Todorovic

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Prior Work and Our Contributionsmentioning

confidence: 99%

Scene Labeling Using Beam Search under Mutex Constraints

Roy

Todorovic

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

Self Cite

View full text Add to dashboard Cite

show abstract

“…Search-based approaches have a long-track record of successfully solving computer vision problems, including structured prediction for scene labeling [13], [14], object localization [15], and boundary detection [16]. Unlike the above related work, search in this paper is not used for inference, but for identifying an optimal CNN architecture and estimating CNN parameters.…”

Section: Beam Searchmentioning

confidence: 99%

Beam search for learning a deep Convolutional Neural Network of 3D shapes

Todorovic

2016

2016 23rd International Conference on Pattern Recognition (ICPR)

Self Cite

View full text Add to dashboard Cite

This paper addresses 3D shape recognition. Recent work typically represents a 3D shape as a set of binary variables corresponding to 3D voxels of a uniform 3D grid centered on the shape, and resorts to deep convolutional neural networks (CNNs) for modeling these binary variables. Robust learning of such CNNs is currently limited by the small datasets of 3D shapes available -an order of magnitude smaller than other common datasets in computer vision. Related work typically deals with the small training datasets using a number of ad hoc, hand-tuning strategies. To address this issue, we formulate CNN learning as a beam search aimed at identifying an optimal CNN architecturenamely, the number of layers, nodes, and their connectivity in the network -as well as estimating parameters of such an optimal CNN. Each state of the beam search corresponds to a candidate CNN. Two types of actions are defined to add new convolutional filters or new convolutional layers to a parent CNN, and thus transition to children states. The utility function of each action is efficiently computed by transferring parameter values of the parent CNN to its children, thereby enabling an efficient beam search. Our experimental evaluation on the 3D ModelNet dataset demonstrates that our model pursuit using the beam search yields a CNN with superior performance on 3D shape classification than the state of the art.

show abstract

“…Some approaches group edges, lines or boundary fragments into contours (Zhu et al, 2007, Arbelaez et al, 2011, Ming et al, 2013, Payet and Todorovic, 2013. The other approaches fit active contour models to images (Kass et al, 1988, Mishra et al, 2011, Dubrovina et al, 2015.…”

Section: Related Workmentioning

confidence: 99%

Detecting Linear Features by Spatial Point Processes

Chai¹,

Schmidt²,

Heipke³

2016

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:This paper proposes a novel approach for linear feature detection. The contribution is twofold: a novel model for spatial point processes and a new method for linear feature detection. It describes a linear feature as a string of points, represents all features in an image as a configuration of a spatial point process, and formulates feature detection as finding the optimal configuration of a spatial point process. Further, a prior term is proposed to favor straight linear configurations, and a data term is constructed to superpose the points on linear features. The proposed approach extracts straight linear features in a global framework. The paper reports ongoing work. As demonstrated in preliminary experiments, globally optimal linear features can be detected.

show abstract

SLEDGE: Sequential Labeling of Image Edges for Boundary Detection

Abstract: Our goal is to detect boundaries of objects

Cited by 19 publications

References 68 publications

Scene Labeling Using Beam Search under Mutex Constraints

Scene Labeling Using Beam Search under Mutex Constraints

Beam search for learning a deep Convolutional Neural Network of 3D shapes

Detecting Linear Features by Spatial Point Processes

Contact Info

Product

Resources

About