A Coarse-to-Fine Instance Segmentation Network with Learning Boundary Representation

• URL: http://arxiv.org/abs/2106.10213v1
• Date: Fri, 18 Jun 2021 16:37:28 GMT
• Title: A Coarse-to-Fine Instance Segmentation Network with Learning Boundary Representation
• Authors: Feng Luo, Bin-Bin Gao, Jiangpeng Yan, Xiu Li
• Abstract summary: Boundary-based instance segmentation has drawn much attention since of its attractive efficiency. Existing methods suffer from the difficulty in long-distance regression. We propose a coarse-to-fine module to address the problem.
• Score: 10.967299485260163
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Boundary-based instance segmentation has drawn much attention since of its attractive efficiency. However, existing methods suffer from the difficulty in long-distance regression. In this paper, we propose a coarse-to-fine module to address the problem. Approximate boundary points are generated at the coarse stage and then features of these points are sampled and fed to a refined regressor for fine prediction. It is end-to-end trainable since differential sampling operation is well supported in the module. Furthermore, we design a holistic boundary-aware branch and introduce instance-agnostic supervision to assist regression. Equipped with ResNet-101, our approach achieves 31.7\% mask AP on COCO dataset with single-scale training and testing, outperforming the baseline 1.3\% mask AP with less than 1\% additional parameters and GFLOPs. Experiments also show that our proposed method achieves competitive performance compared to existing boundary-based methods with a lightweight design and a simple pipeline.

Related papers

• ProtoSeg: A Prototype-Based Point Cloud Instance Segmentation Method [6.632158868486343]
  This paper presents a novel neural network architecture for performing instance segmentation on 3D point clouds. We propose to jointly learn coefficients and prototypes in parallel which can be combined to obtain the instance predictions. The proposed method is not only 28% faster than the state-of-the-art, it also exhibits the lowest standard deviation.
  arXiv  Detail & Related papers  (2024-10-03T10:05:27Z)
• Post-Processing Temporal Action Detection [134.26292288193298]
  Temporal Action Detection (TAD) methods typically take a pre-processing step in converting an input varying-length video into a fixed-length snippet representation sequence. This pre-processing step would temporally downsample the video, reducing the inference resolution and hampering the detection performance in the original temporal resolution. We introduce a novel model-agnostic post-processing method without model redesign and retraining.
  arXiv  Detail & Related papers  (2022-11-27T19:50:37Z)
• BARS: A Benchmark for Airport Runway Segmentation [5.224344210588583]
  Airport runway segmentation can effectively reduce the accident rate during the landing phase. With the rapid development of deep learning (DL), related methods achieve good performance on segmentation tasks. We propose a benchmark for airport runway segmentation, named BARS.
  arXiv  Detail & Related papers  (2022-10-24T02:26:05Z)
• PointInst3D: Segmenting 3D Instances by Points [136.7261709896713]
  We propose a fully-convolutional 3D point cloud instance segmentation method that works in a per-point prediction fashion. We find the key to its success is assigning a suitable target to each sampled point. Our approach achieves promising results on both ScanNet and S3DIS benchmarks.
  arXiv  Detail & Related papers  (2022-04-25T02:41:46Z)
• Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling [52.464516118826765]
  We introduce RandLA-Net, an efficient and lightweight neural architecture to infer per-point semantics for large-scale point clouds. The key to our approach is to use random point sampling instead of more complex point selection approaches. Our RandLA-Net can process 1 million points in a single pass up to 200x faster than existing approaches.
  arXiv  Detail & Related papers  (2021-07-06T05:08:34Z)
• DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution [136.7261709896713]
  We propose a data-driven approach that generates the appropriate convolution kernels to apply in response to the nature of the instances. The proposed method achieves promising results on both ScanetNetV2 and S3DIS. It also improves inference speed by more than 25% over the current state-of-the-art.
  arXiv  Detail & Related papers  (2020-11-26T14:56:57Z)
• The Devil is in the Boundary: Exploiting Boundary Representation for Basis-based Instance Segmentation [85.153426159438]
  We propose Basis based Instance(B2Inst) to learn a global boundary representation that can complement existing global-mask-based methods. Our B2Inst leads to consistent improvements and accurately parses out the instance boundaries in a scene.
  arXiv  Detail & Related papers  (2020-11-26T11:26:06Z)
• 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)
• Towards Bounding-Box Free Panoptic Segmentation [16.4548904544277]
  We introduce a new Bounding-Box Free Network (BBFNet) for panoptic segmentation. BBFNet predicts coarse watershed levels and uses them to detect large instance candidates where boundaries are well defined. For smaller instances, whose boundaries are less reliable, BBFNet also predicts instance centers by means of Hough voting followed by mean-shift to reliably detect small objects.
  arXiv  Detail & Related papers  (2020-02-18T16:34:01Z)

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.