About

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 )

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Libraries

Datasets

Greatest papers with code

Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation

ECCV 2020 tensorflow/models

We view this work as a notable step towards building a simple procedure to harness unlabeled video sequences and extra images to surpass state-of-the-art performance on core computer vision tasks.

OPTICAL FLOW ESTIMATION PANOPTIC SEGMENTATION PATCH MATCHING SCENE SEGMENTATION

Panoptic-DeepLab

10 Oct 2019facebookresearch/detectron2

The semantic segmentation branch is the same as the typical design of any semantic segmentation model (e. g., DeepLab), while the instance segmentation branch is class-agnostic, involving a simple instance center regression.

INSTANCE SEGMENTATION PANOPTIC SEGMENTATION

Panoptic Feature Pyramid Networks

CVPR 2019 facebookresearch/detectron2

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.

INSTANCE SEGMENTATION PANOPTIC SEGMENTATION

End-to-End Object Detection with Transformers

ECCV 2020 open-mmlab/mmdetection

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

OBJECT DETECTION PANOPTIC SEGMENTATION

ResNeSt: Split-Attention Networks

19 Apr 2020open-mmlab/mmdetection

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

IMAGE CLASSIFICATION INSTANCE SEGMENTATION OBJECT DETECTION PANOPTIC SEGMENTATION TRANSFER LEARNING

Feature Pyramid Encoding Network for Real-time Semantic Segmentation

18 Sep 2019osmr/imgclsmob

Although current deep learning methods have achieved impressive results for semantic segmentation, they incur high computational costs and have a huge number of parameters.

PANOPTIC SEGMENTATION REAL-TIME SEMANTIC SEGMENTATION

SOLOv2: Dynamic and Fast Instance Segmentation

NeurIPS 2020 aim-uofa/adet

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.

INSTANCE SEGMENTATION OBJECT DETECTION PANOPTIC SEGMENTATION

Hierarchical Multi-Scale Attention for Semantic Segmentation

21 May 2020NVIDIA/semantic-segmentation

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

 Ranked #1 on Semantic Segmentation on Cityscapes test (using extra training data)

PANOPTIC SEGMENTATION