The Semantic Mutex Watershed for Efficient Bottom-Up Semantic Instance Segmentation

• URL: http://arxiv.org/abs/1912.12717v1
• Date: Sun, 29 Dec 2019 19:48:39 GMT
• Title: The Semantic Mutex Watershed for Efficient Bottom-Up Semantic Instance Segmentation
• Authors: Steffen Wolf, Yuyan Li, Constantin Pape, Alberto Bailoni, Anna Kreshuk, Fred A. Hamprecht
• Abstract summary: We propose a greedy algorithm for joint graph partitioning and labeling. Due to the algorithm's efficiency it can operate directly on pixels without prior over-segmentation of the image into superpixels.
• Score: 15.768804877756384
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Semantic instance segmentation is the task of simultaneously partitioning an image into distinct segments while associating each pixel with a class label. In commonly used pipelines, segmentation and label assignment are solved separately since joint optimization is computationally expensive. We propose a greedy algorithm for joint graph partitioning and labeling derived from the efficient Mutex Watershed partitioning algorithm. It optimizes an objective function closely related to the Symmetric Multiway Cut objective and empirically shows efficient scaling behavior. Due to the algorithm's efficiency it can operate directly on pixels without prior over-segmentation of the image into superpixels. We evaluate the performance on the Cityscapes dataset (2D urban scenes) and on a 3D microscopy volume. In urban scenes, the proposed algorithm combined with current deep neural networks outperforms the strong baseline of `Panoptic Feature Pyramid Networks' by Kirillov et al. (2019). In the 3D electron microscopy images, we show explicitly that our joint formulation outperforms a separate optimization of the partitioning and labeling problems.

Related papers

• Parallel Watershed Partitioning: GPU-Based Hierarchical Image Segmentation [4.560718678349679]
  Many image processing applications rely on partitioning an image into disjoint regions whose pixels are'similar' We show how to use this fully deterministic image partitioning as a pre-processing step to machine learning based semantic segmentation.
  arXiv  Detail & Related papers  (2024-10-11T16:15:43Z)
• View-Consistent Hierarchical 3D Segmentation Using Ultrametric Feature Fields [52.08335264414515]
  We learn a novel feature field within a Neural Radiance Field (NeRF) representing a 3D scene. Our method takes view-inconsistent multi-granularity 2D segmentations as input and produces a hierarchy of 3D-consistent segmentations as output. We evaluate our method and several baselines on synthetic datasets with multi-view images and multi-granular segmentation, showcasing improved accuracy and viewpoint-consistency.
  arXiv  Detail & Related papers  (2024-05-30T04:14:58Z)
• CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation [73.89509052503222]
  This paper presents a simple but performant semi-supervised semantic segmentation approach, called CorrMatch. We observe that the correlation maps not only enable clustering pixels of the same category easily but also contain good shape information. We propose to conduct pixel propagation by modeling the pairwise similarities of pixels to spread the high-confidence pixels and dig out more. Then, we perform region propagation to enhance the pseudo labels with accurate class-agnostic masks extracted from the correlation maps.
  arXiv  Detail & Related papers  (2023-06-07T10:02:29Z)
• High-fidelity Pseudo-labels for Boosting Weakly-Supervised Segmentation [17.804090651425955]
  Image-level weakly-supervised segmentation (WSSS) reduces the usually vast data annotation cost by surrogate segmentation masks during training. Our work is based on two techniques for improving CAMs; importance sampling, which is a substitute for GAP, and the feature similarity loss. We reformulate both techniques based on binomial posteriors of multiple independent binary problems. This has two benefits; their performance is improved and they become more general, resulting in an add-on method that can boost virtually any WSSS method.
  arXiv  Detail & Related papers  (2023-04-05T17:43:57Z)
• UNETR++: Delving into Efficient and Accurate 3D Medical Image Segmentation [93.88170217725805]
  We propose a 3D medical image segmentation approach, named UNETR++, that offers both high-quality segmentation masks as well as efficiency in terms of parameters, compute cost, and inference speed. The core of our design is the introduction of a novel efficient paired attention (EPA) block that efficiently learns spatial and channel-wise discriminative features. Our evaluations on five benchmarks, Synapse, BTCV, ACDC, BRaTs, and Decathlon-Lung, reveal the effectiveness of our contributions in terms of both efficiency and accuracy.
  arXiv  Detail & Related papers  (2022-12-08T18:59:57Z)
• Two-Stream Graph Convolutional Network for Intra-oral Scanner Image Segmentation [133.02190910009384]
  We propose a two-stream graph convolutional network (i.e., TSGCN) to handle inter-view confusion between different raw attributes. Our TSGCN significantly outperforms state-of-the-art methods in 3D tooth (surface) segmentation.
  arXiv  Detail & Related papers  (2022-04-19T10:41:09Z)
• A Novel Falling-Ball Algorithm for Image Segmentation [0.14337588659482517]
  Region-based Falling-Ball algorithm is presented, which is a region-based segmentation algorithm. The proposed algorithm detects the catchment basins by assuming that a ball falling from hilly terrains will stop in a catchment basin.
  arXiv  Detail & Related papers  (2021-05-06T12:41:10Z)
• Deep ensembles based on Stochastic Activation Selection for Polyp Segmentation [82.61182037130406]
  This work deals with medical image segmentation and in particular with accurate polyp detection and segmentation during colonoscopy examinations. Basic architecture in image segmentation consists of an encoder and a decoder. We compare some variant of the DeepLab architecture obtained by varying the decoder backbone.
  arXiv  Detail & Related papers  (2021-04-02T02:07:37Z)
• Improving Image co-segmentation via Deep Metric Learning [1.5076964620370268]
  We propose a novel Triplet loss for Image, called IS-Triplet loss for short, and combine it with traditional image segmentation loss. We apply the proposed approach to image co-segmentation and test it on the SBCoseg dataset and the Internet dataset.
  arXiv  Detail & Related papers  (2021-03-19T07:30:42Z)
• PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation [96.76882806139251]
  We propose a point-wise affinity propagation module based on the Feature Pyramid Network (FPN) framework, named PointFlow. Rather than dense affinity learning, a sparse affinity map is generated upon selected points between the adjacent features. Experimental results on three different aerial segmentation datasets suggest that the proposed method is more effective and efficient than state-of-the-art general semantic segmentation methods.
  arXiv  Detail & Related papers  (2021-03-11T09:42:32Z)

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.