Panoptic Segmentation

85 papers with code • 10 benchmarks • 14 datasets

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 )


Use these libraries to find Panoptic Segmentation models and implementations

Most implemented papers

Mask R-CNN

matterport/Mask_RCNN ICCV 2017

Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance.

ResNeSt: Split-Attention Networks

zhanghang1989/ResNeSt 19 Apr 2020

It is well known that featuremap attention and multi-path representation are important for visual recognition.

End-to-End Object Detection with Transformers

facebookresearch/detr ECCV 2020

We present a new method that views object detection as a direct set prediction problem.

SOLOv2: Dynamic and Fast Instance Segmentation

WXinlong/SOLO NeurIPS 2020

Importantly, we take one step further by dynamically learning the mask head of the object segmenter such that the mask head is conditioned on the location.

Panoptic Feature Pyramid Networks

facebookresearch/detectron2 CVPR 2019

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.

ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation

sacmehta/ESPNet ECCV 2018

We introduce a fast and efficient convolutional neural network, ESPNet, for semantic segmentation of high resolution images under resource constraints.

CenterMask : Real-Time Anchor-Free Instance Segmentation

youngwanLEE/CenterMask arXiv 2019

We hope that CenterMask and VoVNetV2 can serve as a solid baseline of real-time instance segmentation and backbone network for various vision tasks, respectively.

Hierarchical Multi-Scale Attention for Semantic Segmentation

NVIDIA/semantic-segmentation 21 May 2020

Multi-scale inference is commonly used to improve the results of semantic segmentation.

PVTv2: Improved Baselines with Pyramid Vision Transformer

whai362/PVT 25 Jun 2021

We hope this work will facilitate state-of-the-art Transformer researches in computer vision.

Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation

bowenc0221/panoptic-deeplab CVPR 2020

In this work, we introduce Panoptic-DeepLab, a simple, strong, and fast system for panoptic segmentation, aiming to establish a solid baseline for bottom-up methods that can achieve comparable performance of two-stage methods while yielding fast inference speed.