Published November 27, 2019 | Version Submitted
Discussion Paper Open

PanDA: Panoptic Data Augmentation

  • 1. ROR icon California Institute of Technology

Abstract

The recently proposed panoptic segmentation task presents a significant challenge of image understanding with computer vision by unifying semantic segmentation and instance segmentation tasks. In this paper we present an efficient and novel panoptic data augmentation (PanDA) method which operates exclusively in pixel space, requires no additional data or training, and is computationally cheap to implement. By retraining original state-of-the-art models on PanDA augmented datasets generated with a single frozen set of parameters, we show robust performance gains in panoptic segmentation, instance segmentation, as well as detection across models, backbones, dataset domains, and scales. Finally, the effectiveness of unrealistic-looking training images synthesized by PanDA suggest that one should rethink the need for image realism for efficient data augmentation.

Attached Files

Submitted - 1911.12317.pdf

Files

1911.12317.pdf

Files (9.2 MB)

Name Size Download all
md5:b352f93e3c7a0dfb47c94f8ebc1eb306
9.2 MB Preview Download

Additional details

Identifiers

Eprint ID
103461
Resolver ID
CaltechAUTHORS:20200526-134149667

Related works

Dates

Created
2020-05-26
Created from EPrint's datestamp field
Updated
2023-06-02
Created from EPrint's last_modified field

Caltech Custom Metadata

Caltech groups
Division of Biology and Biological Engineering (BBE)