DeepAI AI Chat
Log In Sign Up

PanDA: Panoptic Data Augmentation

by   Yang Liu, et al.

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. We retrain the original state-of-the-art UPSNet panoptic segmentation model on PanDA augmented Cityscapes dataset, and demonstrate all-round performance improvement upon the original model. We also show that PanDA is effective across scales from 10 to 30,000 images, as well as generalizable to Microsoft COCO panoptic segmentation task. Finally, the effectiveness of PanDA generated unrealistic-looking training images suggest that we should rethink about optimizing levels of image realism for efficient data augmentation.


page 2

page 3

page 4

page 5

page 11

page 12


PointTrack++ for Effective Online Multi-Object Tracking and Segmentation

Multiple-object tracking and segmentation (MOTS) is a novel computer vis...

InsMix: Towards Realistic Generative Data Augmentation for Nuclei Instance Segmentation

Nuclei Segmentation from histology images is a fundamental task in digit...

Learning to Detect Every Thing in an Open World

Many open-world applications require the detection of novel objects, yet...

Augmentation Backdoors

Data augmentation is used extensively to improve model generalisation. H...