Image segmentation groups pixels with different semantics, eg, category or instance
membership. Each choice of semantics defines a task. While only the semantics of each task …

Training a convolutional neural network (CNN) to detect infrared small targets in a fully
supervised manner has gained remarkable research interests in recent years, but is highly …

Panoptic segmentation involves a combination of joint semantic segmentation and instance
segmentation, where image contents are divided into two types: things and stuff. We present …

Open-vocabulary instance segmentation aims at segmenting novel classes without mask
annotations. It is an important step toward reducing laborious human supervision. Most …

Several unsupervised image segmentation approaches have been proposed which
eliminate the need for dense manually-annotated segmentation masks; current models …

We introduce a new image segmentation task, called Entity Segmentation (ES), which aims
to segment all visual entities (objects and stuffs) in an image without predicting their …

Weakly-supervised image segmentation has recently attracted increasing research
attentions, aiming to avoid the expensive pixel-wise labeling. In this paper, we present an …

In instance-level detection tasks (eg, object detection), reducing input resolution is an easy
option to improve runtime efficiency. However, this option severely hurts the detection …

In this paper, we propose a new approach to applying point-level annotations for weakly-
supervised panoptic segmentation. Instead of the dense pixel-level labels used by fully …

Abstract Panoptic Part Segmentation (PPS) aims to unify panoptic segmentation and part
segmentation into one task. Previous work mainly utilizes separated approaches to handle …