Fast Panoptic Segmentation Network
This work addresses the need for faster panoptic segmentation in computer vision applications, offering a method that is faster than existing approaches while maintaining competitive performance, though it is incremental in its improvements.
The authors tackled panoptic segmentation by proposing FPSNet, an end-to-end network that avoids costly instance mask predictions, achieving a Panoptic Quality score of 55.1% on Cityscapes with prediction times as low as 114 milliseconds for high-resolution images.
In this work, we present an end-to-end network for fast panoptic segmentation. This network, called Fast Panoptic Segmentation Network (FPSNet), does not require computationally costly instance mask predictions or merging heuristics. This is achieved by casting the panoptic task into a custom dense pixel-wise classification task, which assigns a class label or an instance id to each pixel. We evaluate FPSNet on the Cityscapes and Pascal VOC datasets, and find that FPSNet is faster than existing panoptic segmentation methods, while achieving better or similar panoptic segmentation performance. On the Cityscapes validation set, we achieve a Panoptic Quality score of 55.1%, at prediction times of 114 milliseconds for images with a resolution of 1024x2048 pixels. For lower resolutions of the Cityscapes dataset and for the Pascal VOC dataset, FPSNet runs at 22 and 35 frames per second, respectively.