Prevalent semantic segmentation solutions are, in essence, a dense discriminative classifier
of p (class| pixel feature). Though straightforward, this de facto paradigm neglects the …

Prevalent state-of-the-art instance segmentation methods fall into a query-based scheme, in
which instance masks are derived by querying the image feature using a set of instance …

Optical flow is an indispensable building block for various important computer vision tasks,
including motion estimation, object tracking, and disparity measurement. In this work, we …

Abstract The popularity of Contrastive Language-Image Pre-training (CLIP) has propelled its
application to diverse downstream vision tasks. To improve its capacity on downstream …

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 …

The combination of infrared and visible videos aims to gather more comprehensive feature
information from multiple sources and reach superior results on various practical tasks, such …

The task of point cloud segmentation, comprising semantic, instance, and panoptic
segmentation, has been mainly tackled by designing task-specific network architectures …

Federated Graph Learning is a privacy-preserving collaborative approach for training a
shared model on graph-structured data in the distributed environment. However, in real …

As the size of transformer-based models continues to grow, fine-tuning these large-scale
pretrained vision models for new tasks has become increasingly parameter-intensive …