DeepAI AI Chat
Log In Sign Up

DeeperLab: Single-Shot Image Parser

by   Tien-Ju Yang, et al.

We present a single-shot, bottom-up approach for whole image parsing. Whole image parsing, also known as Panoptic Segmentation, generalizes the tasks of semantic segmentation for 'stuff' classes and instance segmentation for 'thing' classes, assigning both semantic and instance labels to every pixel in an image. Recent approaches to whole image parsing typically employ separate standalone modules for the constituent semantic and instance segmentation tasks and require multiple passes of inference. Instead, the proposed DeeperLab image parser performs whole image parsing with a significantly simpler, fully convolutional approach that jointly addresses the semantic and instance segmentation tasks in a single-shot manner, resulting in a streamlined system that better lends itself to fast processing. For quantitative evaluation, we use both the instance-based Panoptic Quality (PQ) metric and the proposed region-based Parsing Covering (PC) metric, which better captures the image parsing quality on 'stuff' classes and larger object instances. We report experimental results on the challenging Mapillary Vistas dataset, in which our single model achieves 31.95 frames per second (fps) on GPU or near real-time speed (22.6 fps on GPU) with reduced accuracy.


page 4

page 8


EOLO: Embedded Object Segmentation only Look Once

In this paper, we introduce an anchor-free and single-shot instance segm...

PolarMask: Single Shot Instance Segmentation with Polar Representation

In this paper, we introduce an anchor-box free and single shot instance ...


We present Panoptic-DeepLab, a bottom-up and single-shot approach for pa...

SSAP: Single-Shot Instance Segmentation With Affinity Pyramid

Recently, proposal-free instance segmentation has received increasing at...

Single Network Panoptic Segmentation for Street Scene Understanding

In this work, we propose a single deep neural network for panoptic segme...

Learning Instance Occlusion for Panoptic Segmentation

Recently, the vision community has shown renewed interest in the effort ...

Single-shot Path Integrated Panoptic Segmentation

Panoptic segmentation, which is a novel task of unifying instance segmen...