Towards Bounding-Box Free Panoptic Segmentation

• URL: http://arxiv.org/abs/2002.07705v3
• Date: Mon, 27 Jul 2020 17:48:08 GMT
• Title: Towards Bounding-Box Free Panoptic Segmentation
• Authors: Ujwal Bonde and Pablo F. Alcantarilla and Stefan Leutenegger
• Abstract summary: 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.
• Score: 16.4548904544277
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work we introduce a new Bounding-Box Free Network (BBFNet) for panoptic segmentation. Panoptic segmentation is an ideal problem for proposal-free methods as it already requires per-pixel semantic class labels. We use this observation to exploit class boundaries from off-the-shelf semantic segmentation networks and refine them to predict instance labels. Towards this goal 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. A novel triplet loss network helps merging fragmented instances while refining boundary pixels. Our approach is distinct from previous works in panoptic segmentation that rely on a combination of a semantic segmentation network with a computationally costly instance segmentation network based on bounding box proposals, such as Mask R-CNN, to guide the prediction of instance labels using a Mixture-of-Expert (MoE) approach. We benchmark our proposal-free method on Cityscapes and Microsoft COCO datasets and show competitive performance with other MoE based approaches while outperforming existing non-proposal based methods on the COCO dataset. We show the flexibility of our method using different semantic segmentation backbones.

Related papers

• BAISeg: Boundary Assisted Weakly Supervised Instance Segmentation [9.6046915661065]
  How to extract instance-level masks without instance-level supervision is the main challenge of weakly supervised instance segmentation (WSIS) Popular WSIS methods estimate a displacement field (DF) via learning inter-pixel relations and perform clustering to identify instances. We propose Boundary-Assisted Instance (BAISeg), which is a novel paradigm for WSIS that realizes instance segmentation with pixel-level annotations.
  arXiv  Detail & Related papers  (2024-05-27T15:14:09Z)
• Label-efficient Segmentation via Affinity Propagation [27.016747627689288]
  Weakly-supervised segmentation with label-efficient sparse annotations has attracted increasing research attention to reduce the cost of laborious pixel-wise labeling process. We formulate the affinity modeling as an affinity propagation process, and propose a local and a global pairwise affinity terms to generate accurate soft pseudo labels. An efficient algorithm is also developed to reduce significantly the computational cost.
  arXiv  Detail & Related papers  (2023-10-16T15:54:09Z)
• Side Adapter Network for Open-Vocabulary Semantic Segmentation [69.18441687386733]
  This paper presents a new framework for open-vocabulary semantic segmentation with the pre-trained vision-language model, named Side Adapter Network (SAN) A side network is attached to a frozen CLIP model with two branches: one for predicting mask proposals, and the other for predicting attention bias. Our approach significantly outperforms other counterparts, with up to 18 times fewer trainable parameters and 19 times faster inference speed.
  arXiv  Detail & Related papers  (2023-02-23T18:58:28Z)
• 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)
• 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)
• Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation [21.296942497092402]
  We present a fast and robust LiDAR point cloud panoptic segmentation framework, referred to as Panoptic-PolarNet. We learn both semantic segmentation and class-agnostic instance clustering in a single inference network using a polar Bird's Eye View representation. Our experiments show that Panoptic-PolarNet outperforms the baseline methods on Semantic KITTI and nuScenes datasets with an almost real-time inference speed.
  arXiv  Detail & Related papers  (2021-03-27T18:31:40Z)
• SPICE: Semantic Pseudo-labeling for Image Clustering [5.357314252311141]
  SPICE is a Semantic Pseudo-labeling framework for Image ClustEring. It generates pseudo-labels via self-learning and uses the pseudo-label-based classification loss to train a deep clustering network. Our method improves the current best results by about 10% in terms of adjusted rand index, normalized mutual information, and clustering accuracy.
  arXiv  Detail & Related papers  (2021-03-17T00:52:27Z)
• Towards Efficient Scene Understanding via Squeeze Reasoning [71.1139549949694]
  We propose a novel framework called Squeeze Reasoning. Instead of propagating information on the spatial map, we first learn to squeeze the input feature into a channel-wise global vector. We show that our approach can be modularized as an end-to-end trained block and can be easily plugged into existing networks.
  arXiv  Detail & Related papers  (2020-11-06T12:17:01Z)
• Deep Affinity Net: Instance Segmentation via Affinity [48.498706304017674]
  Deep Affinity Net is an effective affinity-based approach accompanied with a new graph partitioning algorithm Cascade-GAEC. It achieves the best single-shot result as well as the fastest running time among all affinity-based models. It also outperforms the region-based method Mask R-CNN.
  arXiv  Detail & Related papers  (2020-03-15T15:22:56Z)

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.