Adversarial attacks and defenses in machine learning and deep neural network (DNN) have
been gaining significant attention due to the rapidly growing applications of deep learning in …

Over the past decade, deep learning has revolutionized conventional tasks that rely on hand-
craft feature extraction with its strong feature learning capability, leading to substantial …

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 …

We devise deep nearest centroids (DNC), a conceptually elegant yet surprisingly effective
network for large-scale visual recognition, by revisiting Nearest Centroids, one of the most …

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

Depth estimation from monocular images is pivotal for real-world visual perception systems.
While current learning-based depth estimation models train and test on meticulously curated …

Instance segmentation in videos, which aims to segment and track multiple objects in video
frames, has garnered a flurry of research attention in recent years. In this paper, we present …

Accurate depth estimation under out-of-distribution (OoD) scenarios, such as adverse
weather conditions, sensor failure, and noise contamination, is desirable for safety-critical …

Despite the impressive achievements of Deep Neural Networks (DNNs) in computer vision,
their vulnerability to adversarial attacks remains a critical concern. Extensive research has …