Browse > Computer Vision > Semantic Segmentation > Panoptic Segmentation

# Panoptic Segmentation Edit

9 papers with code · Computer Vision

Panoptic segmentation unifies the typically distinct tasks of semantic segmentation (assign a class label to each pixel) and instance segmentation (detect and segment each object instance).

( Image credit: Detectron2 )

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

# Panoptic Feature Pyramid Networks

In this work, we perform a detailed study of this minimally extended version of Mask R-CNN with FPN, which we refer to as Panoptic FPN, and show it is a robust and accurate baseline for both tasks.

8,038

# UPSNet: A Unified Panoptic Segmentation Network

More importantly, we introduce a parameter-free panoptic head which solves the panoptic segmentation via pixel-wise classification.

#2 best model for Panoptic Segmentation on Cityscapes val (using extra training data)

475

Given an input image and a point $(x, y)$, it generates a mask for the object located at $(x, y)$.

260

# CenterMask : Real-Time Anchor-Free Instance Segmentation

Plugged into the FCOS object detector, the SAG-Mask branch predicts a segmentation mask on each box with the spatial attention map that helps to focus on informative pixels and suppress noise.

218

# Seamless Scene Segmentation

In this work we introduce a novel, CNN-based architecture that can be trained end-to-end to deliver seamless scene segmentation results.

180

# Panoptic Segmentation

We propose and study a task we name panoptic segmentation (PS).

#3 best model for Panoptic Segmentation on Cityscapes val (using extra training data)

171

# Weakly- and Semi-Supervised Panoptic Segmentation

We present a weakly supervised model that jointly performs both semantic- and instance-segmentation -- a particularly relevant problem given the substantial cost of obtaining pixel-perfect annotation for these tasks.

131

# Single Network Panoptic Segmentation for Street Scene Understanding

7 Feb 2019DdeGeus/single-network-panoptic-segmentation

Our network is evaluated on two street scene datasets: Cityscapes and Mapillary Vistas.

17

# Generator evaluator-selector net: a modular approach for panoptic segmentation

The generator/evaluator approach for this case consists of two independent convolutional neural nets: a generator net that suggests variety segments corresponding to objects and distinct regions in the image and an evaluator net that chooses the best segments to be merged into the segmentation map.

5