SharpContour: A Contour-based Boundary Refinement Approach for Efficient and Accurate Instance Segmentation

• URL: http://arxiv.org/abs/2203.13312v1
• Date: Thu, 24 Mar 2022 19:37:20 GMT
• Title: SharpContour: A Contour-based Boundary Refinement Approach for Efficient and Accurate Instance Segmentation
• Authors: Chenming Zhu, Xuanye Zhang, Yanran Li, Liangdong Qiu, Kai Han, Xiaoguang Han
• Abstract summary: We propose an efficient contour-based boundary refinement approach, named SharpContour, to tackle the segmentation of boundary area. Our method deforms the contour iteratively by updating offsets in a discrete manner. Experiments show that SharpContour achieves competitive gains whilst preserving high efficiency.
• Score: 29.051499127975703
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Excellent performance has been achieved on instance segmentation but the quality on the boundary area remains unsatisfactory, which leads to a rising attention on boundary refinement. For practical use, an ideal post-processing refinement scheme are required to be accurate, generic and efficient. However, most of existing approaches propose pixel-wise refinement, which either introduce a massive computation cost or design specifically for different backbone models. Contour-based models are efficient and generic to be incorporated with any existing segmentation methods, but they often generate over-smoothed contour and tend to fail on corner areas. In this paper, we propose an efficient contour-based boundary refinement approach, named SharpContour, to tackle the segmentation of boundary area. We design a novel contour evolution process together with an Instance-aware Point Classifier. Our method deforms the contour iteratively by updating offsets in a discrete manner. Differing from existing contour evolution methods, SharpContour estimates each offset more independently so that it predicts much sharper and accurate contours. Notably, our method is generic to seamlessly work with diverse existing models with a small computational cost. Experiments show that SharpContour achieves competitive gains whilst preserving high efficiency

Related papers

• A Deep Active Contour Model for Delineating Glacier Calving Fronts [17.061463565692456]
  Recent studies have shown that combining segmentation with edge detection can improve the accuracy of calving front detectors. We propose a model for explicit contour detection that does not incorporate any dense predictions as intermediate steps. The proposed approach, called Charting Outlines by Recurrent Adaptation'' (COBRA), combines Convolutional Neural Networks (CNNs) for feature extraction and active contour models for the delineation.
  arXiv  Detail & Related papers  (2023-07-07T08:45:46Z)
• Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flows [54.050498411883495]
  We develop a novel training method for generative models, such as Generative Adversarial Networks and Normalizing Flows. We show that achieving a specified precision-recall trade-off corresponds to minimizing a unique $f$-divergence from a family we call the textitPR-divergences. Our approach improves the performance of existing state-of-the-art models like BigGAN in terms of either precision or recall when tested on datasets such as ImageNet.
  arXiv  Detail & Related papers  (2023-05-30T10:07:17Z)
• LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds [62.49198183539889]
  We propose a label-efficient semantic segmentation pipeline for outdoor scenes with LiDAR point clouds. Our method co-designs an efficient labeling process with semi/weakly supervised learning. Our proposed method is even highly competitive compared to the fully supervised counterpart with 100% labels.
  arXiv  Detail & Related papers  (2022-10-14T19:13:36Z)
• PNM: Pixel Null Model for General Image Segmentation [17.971090313814447]
  We present a prior model that weights each pixel according to its probability of being correctly classified by a random segmenter. Experiments on semantic, instance, and panoptic segmentation tasks over three datasets confirm that PNM consistently improves the segmentation quality. We propose a new metric, textitPNM IoU, which perceives the boundary sharpness and better reflects the model segmentation performance in error-prone regions.
  arXiv  Detail & Related papers  (2022-03-13T15:17:41Z)
• SCR: Smooth Contour Regression with Geometric Priors [10.141085397402314]
  SCR is a method that captures resolution-free object contours as complex periodic functions. We benchmark SCR on the popular COCO 2017 instance segmentation dataset, and show its competitiveness against existing algorithms. We also design a compact version of our network, which we benchmark on embedded hardware with a wide range of power targets.
  arXiv  Detail & Related papers  (2022-02-08T11:07:51Z)
• ContourRender: Detecting Arbitrary Contour Shape For Instance Segmentation In One Pass [48.57232627854642]
  We argue that the difficulty in regressing the contour points in one pass is mainly due to the ambiguity when discretizing a smooth contour into a polygon. To address the ambiguity, we propose a novel differentiable rendering-based approach named textbfContourRender. It first predicts a contour generated by an invertible shape signature, and then optimize the contour with the more stable silhouette by converting it to a contour mesh and rendering the mesh to a 2D map.
  arXiv  Detail & Related papers  (2021-06-07T07:23:03Z)
• BoundarySqueeze: Image Segmentation as Boundary Squeezing [104.43159799559464]
  We propose a novel method for fine-grained high-quality image segmentation of both objects and scenes. Inspired by dilation and erosion from morphological image processing techniques, we treat the pixel level segmentation problems as squeezing object boundary. Our method yields large gains on COCO, Cityscapes, for both instance and semantic segmentation and outperforms previous state-of-the-art PointRend in both accuracy and speed under the same setting.
  arXiv  Detail & Related papers  (2021-05-25T04:58:51Z)
• Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation [51.59290734837372]
  We propose a conceptually simple yet effective post-processing refinement framework to improve the boundary quality. The proposed BPR framework yields significant improvements over the Mask R-CNN baseline on Cityscapes benchmark. By applying the BPR framework to the PolyTransform + SegFix baseline, we reached 1st place on the Cityscapes leaderboard.
  arXiv  Detail & Related papers  (2021-04-12T07:10:48Z)
• Neural Subdivision [58.97214948753937]
  This paper introduces Neural Subdivision, a novel framework for data-driven coarseto-fine geometry modeling. We optimize for the same set of network weights across all local mesh patches, thus providing an architecture that is not constrained to a specific input mesh, fixed genus, or category. We demonstrate that even when trained on a single high-resolution mesh our method generates reasonable subdivisions for novel shapes.
  arXiv  Detail & Related papers  (2020-05-04T20:03:21Z)

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.