Liu, Yang and Perona, Pietro and Meister, Markus (2019) PanDA: Panoptic Data Augmentation. . (Unpublished) https://resolver.caltech.edu/CaltechAUTHORS:20200526-134149667
![]() |
PDF
- Submitted Version
Creative Commons Attribution. 9MB |
Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20200526-134149667
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.
Item Type: | Report or Paper (Discussion Paper) | ||||||
---|---|---|---|---|---|---|---|
Related URLs: |
| ||||||
ORCID: |
| ||||||
Subject Keywords: | Data Augmentation, Panoptic Segmentation, Scene Understanding, Image Synthesis | ||||||
Record Number: | CaltechAUTHORS:20200526-134149667 | ||||||
Persistent URL: | https://resolver.caltech.edu/CaltechAUTHORS:20200526-134149667 | ||||||
Usage Policy: | No commercial reproduction, distribution, display or performance rights in this work are provided. | ||||||
ID Code: | 103461 | ||||||
Collection: | CaltechAUTHORS | ||||||
Deposited By: | Tony Diaz | ||||||
Deposited On: | 26 May 2020 22:54 | ||||||
Last Modified: | 26 May 2020 22:54 |
Repository Staff Only: item control page