Pith. sign in

REVIEW

Vec2Instance: Parameterization for Deep Instance Segmentation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2010.02725 v1 pith:PWNNXRWJ submitted 2020-10-06 cs.CV cs.LGeess.IV

classification cs.CVcs.LGeess.IV
keywords segmentationvec2instanceinstanceaccuracydeepapproacharchitecturecomplex
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Current advances in deep learning is leading to human-level accuracy in computer vision tasks such as object classification, localization, semantic segmentation, and instance segmentation. In this paper, we describe a new deep convolutional neural network architecture called Vec2Instance for instance segmentation. Vec2Instance provides a framework for parametrization of instances, allowing convolutional neural networks to efficiently estimate the complex shapes of instances around their centroids. We demonstrate the feasibility of the proposed architecture with respect to instance segmentation tasks on satellite images, which have a wide range of applications. Moreover, we demonstrate the usefulness of the new method for extracting building foot-prints from satellite images. Total pixel-wise accuracy of our approach is 89\%, near the accuracy of the state-of-the-art Mask RCNN (91\%). Vec2Instance is an alternative approach to complex instance segmentation pipelines, offering simplicity and intuitiveness. The code developed under this study is available in the Vec2Instance GitHub repository, https://github.com/lakmalnd/Vec2Instance

Discussion (0). Continue with ORCID to comment.

Pith tools