Vec2Instance: Parameterization for Deep Instance Segmentation
- URL: http://arxiv.org/abs/2010.02725v1
- Date: Tue, 6 Oct 2020 13:51:02 GMT
- Title: Vec2Instance: Parameterization for Deep Instance Segmentation
- Authors: N. Lakmal Deshapriya, Matthew N. Dailey, Manzul Kumar Hazarika,
Hiroyuki Miyazaki
- Abstract summary: 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.
Total pixel-wise accuracy of our approach is 89%, near the accuracy of the state-of-the-art Mask RCNN (91%)
- Score: 0.17205106391379021
- License: http://creativecommons.org/licenses/by/4.0/
- 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
Related papers
- Synthetic Instance Segmentation from Semantic Image Segmentation Masks [37.54211062233899]
We propose a novel paradigm called synthetic instance segmentation (SISeg)
SISeg does not require training a semantic or/and instance segmentation model and avoids the need for instance-level image annotations.
It can achieve competitive results compared to the state-of-the-art fully-supervised instance segmentation methods.
arXiv Detail & Related papers (2023-08-02T05:13:02Z) - Sparse Instance Activation for Real-Time Instance Segmentation [72.23597664935684]
We propose a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation.
SparseInst has extremely fast inference speed and achieves 40 FPS and 37.9 AP on the COCO benchmark.
arXiv Detail & Related papers (2022-03-24T03:15:39Z) - SOLO: A Simple Framework for Instance Segmentation [84.00519148562606]
"instance categories" assigns categories to each pixel within an instance according to the instance's location.
"SOLO" is a simple, direct, and fast framework for instance segmentation with strong performance.
Our approach achieves state-of-the-art results for instance segmentation in terms of both speed and accuracy.
arXiv Detail & Related papers (2021-06-30T09:56:54Z) - INSTA-YOLO: Real-Time Instance Segmentation [2.9769485817170387]
We propose Insta-YOLO, a novel one-stage end-to-end deep learning model for real-time instance segmentation.
Instead of pixel-wise prediction, our model predicts instances as object contours represented by 2D points in Cartesian space.
We evaluate our model on three datasets, namely, Carvana,Cityscapes and Airbus.
arXiv Detail & Related papers (2021-02-12T21:17:29Z) - Instance and Panoptic Segmentation Using Conditional Convolutions [96.7275593916409]
We propose a simple yet effective framework for instance and panoptic segmentation, termed CondInst.
We show that CondInst can achieve improved accuracy and inference speed on both instance and panoptic segmentation tasks.
arXiv Detail & Related papers (2021-02-05T06:57:02Z) - Unifying Instance and Panoptic Segmentation with Dynamic Rank-1
Convolutions [109.2706837177222]
DR1Mask is the first panoptic segmentation framework that exploits a shared feature map for both instance and semantic segmentation.
As a byproduct, DR1Mask is 10% faster and 1 point in mAP more accurate than previous state-of-the-art instance segmentation network BlendMask.
arXiv Detail & Related papers (2020-11-19T12:42:10Z) - Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with
Deep Metric Learning [5.699350798684963]
We propose a simple, yet efficient algorithm for 3D instance segmentation using deep metric learning.
For high-level intelligent tasks from a large scale scene, 3D instance segmentation recognizes individual instances of objects.
We demonstrate the state-of-the-art performance of our algorithm in the ScanNet 3D instance segmentation benchmark on AP score.
arXiv Detail & Related papers (2020-07-07T02:17:44Z) - PointINS: Point-based Instance Segmentation [117.38579097923052]
Mask representation in instance segmentation with Point-of-Interest (PoI) features is challenging because learning a high-dimensional mask feature for each instance requires a heavy computing burden.
We propose an instance-aware convolution, which decomposes this mask representation learning task into two tractable modules.
Along with instance-aware convolution, we propose PointINS, a simple and practical instance segmentation approach.
arXiv Detail & Related papers (2020-03-13T08:24:58Z) - Conditional Convolutions for Instance Segmentation [109.2706837177222]
We propose a simple yet effective instance segmentation framework, termed CondInst.
We employ dynamic instance-aware networks, conditioned on instances.
We demonstrate a simpler instance segmentation method that can achieve improved performance in both accuracy and inference speed.
arXiv Detail & Related papers (2020-03-12T08:42:36Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.