This paper presents a new mechanism to facilitate the training of mask transformers for
efficient panoptic segmentation, democratizing its deployment. We observe that due to the …

Panoptic occupancy poses a novel challenge by aiming to integrate instance occupancy
and semantic occupancy within a unified framework. However, there is still a lack of efficient …

In this paper, we introduce a novel panoptic segmentation method called the Mask-Pyramid
Network. Existing Mask RCNN-based methods first generate a large number of box …

A powerful architecture for universal segmentation relies on transformers that encode multi-
scale image features and decode object queries into mask predictions. With efficiency being …

Computer vision has emerged as a prominent study field in recent years, with practical
applications in the current era. Image segmentation is a major research field in computer …

This thesis explores the frontier of visual perception in computer vision by leveraging the
capabilities of Vision Transformers (ViTs) to create a unified framework that addresses cross …