Related papers: Fully Convolutional Networks for Panoptic Segmentation

Fully Convolutional Networks for Panoptic Segmentation

URL: http://arxiv.org/abs/2012.00720v2
Date: Sat, 3 Apr 2021 04:28:54 GMT
Title: Fully Convolutional Networks for Panoptic Segmentation
Authors: Yanwei Li, Hengshuang Zhao, Xiaojuan Qi, Liwei Wang, Zeming Li, Jian Sun, Jiaya Jia
Abstract summary: We present a conceptually simple, strong, and efficient framework for panoptic segmentation, called Panoptic FCN. Our approach aims to represent and predict foreground things and background stuff in a unified fully convolutional pipeline. Panoptic FCN encodes each object instance or stuff category into a specific kernel weight with the proposed kernel generator.
Score: 91.84686839549488
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: In this paper, we present a conceptually simple, strong, and efficient framework for panoptic segmentation, called Panoptic FCN. Our approach aims to represent and predict foreground things and background stuff in a unified fully convolutional pipeline. In particular, Panoptic FCN encodes each object instance or stuff category into a specific kernel weight with the proposed kernel generator and produces the prediction by convolving the high-resolution feature directly. With this approach, instance-aware and semantically consistent properties for things and stuff can be respectively satisfied in a simple generate-kernel-then-segment workflow. Without extra boxes for localization or instance separation, the proposed approach outperforms previous box-based and -free models with high efficiency on COCO, Cityscapes, and Mapillary Vistas datasets with single scale input. Our code is made publicly available at https://github.com/Jia-Research-Lab/PanopticFCN.

Related papers

Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision [88.71403886207071]
We present a conceptually simple, strong, and efficient framework for fully- and weakly-supervised panoptic segmentation, called Panoptic FCN. Our approach aims to represent and predict foreground things and background stuff in a unified fully convolutional pipeline. Panoptic FCN encodes each object instance or stuff category with the proposed kernel generator and produces the prediction by convolving the high-resolution feature directly.
arXiv Detail & Related papers (2021-08-17T15:28:53Z)
Dynamic Convolution for 3D Point Cloud Instance Segmentation [146.7971476424351]
We propose an approach to instance segmentation from 3D point clouds based on dynamic convolution. We gather homogeneous points that have identical semantic categories and close votes for the geometric centroids. The proposed approach is proposal-free, and instead exploits a convolution process that adapts to the spatial and semantic characteristics of each instance.
arXiv Detail & Related papers (2021-07-18T09:05:16Z)
K-Net: Towards Unified Image Segmentation [78.32096542571257]
The framework, named K-Net, segments both instances and semantic categories consistently by a group of learnable kernels. K-Net can be trained in an end-to-end manner with bipartite matching, and its training and inference are naturally NMS-free and box-free.
arXiv Detail & Related papers (2021-06-28T17:18:21Z)
Inferring community characteristics in labelled networks [6.85316573653194]
We introduce a new generative model, the feature-first block model (FFBM) We present a method to efficiently sample from the posterior distribution of the FFBM parameters. The main advantages of the proposed approach are that the whole feature-space is used automatically, and features can be rank-ordered implicitly according to impact.
arXiv Detail & Related papers (2021-05-28T12:07:10Z)
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)
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)
EPSNet: Efficient Panoptic Segmentation Network with Cross-layer Attention Fusion [5.815742965809424]
We propose an Efficient Panoptic Network (EPSNet) to tackle the panoptic segmentation tasks with fast inference speed. Basically, EPSNet generates masks based on simple linear combination of prototype masks and mask coefficients. To enhance the quality of shared prototypes, we adopt a module called "cross-layer attention fusion module"
arXiv Detail & Related papers (2020-03-23T09:11:44Z)
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.