Open-vocabulary segmentation is a challenging task requiring segmenting and recognizing
objects from an open set of categories in diverse environments. One way to address this …

Abstract Universal Image Segmentation is not a new concept. Past attempts to unify image
segmentation include scene parsing, panoptic segmentation, and, more recently, new …

One-to-one set matching is a key design for DETR to establish its end-to-end capability, so
that object detection does not require a hand-crafted NMS (non-maximum suppression) to …

Panoptic segmentation assigns semantic and instance ID labels to every pixel of an image.
As permutations of instance IDs are also valid solutions, the task requires learning of high …

Transformer has shown excellent performance in remote sensing field with long-range
modeling capabilities. Remote sensing video (RSV) moving object detection and tracking …

Modern detection transformers (DETRs) use a set of object queries to predict a list of
bounding boxes, sort them by their classification confidence scores, and select the top …

We present CLUSTSEG, a general, transformer-based framework that tackles different
image segmentation tasks (ie, superpixel, semantic, instance, and panoptic) through a …

This paper presents ClusterFormer, a universal vision model that is based on the Clustering
paradigm with TransFormer. It comprises two novel designs: 1) recurrent cross-attention …

Visual segmentation seeks to partition images, video frames, or point clouds into multiple
segments or groups. This technique has numerous real-world applications, such as …

Recent attention in instance segmentation has focused on query-based models. Despite
being non-maximum suppression (NMS)-free and end-to-end, the superiority of these …