Abstract We propose Clustering Mask Transformer (CMT-DeepLab), a transformer-based
framework for panoptic segmentation designed around clustering. It rethinks the existing …

Nowadays, vehicles with a high level of automation are being driven everywhere. With the
apparent success of autonomous driving technology, we keep working to achieve fully …

Scene text detection and document layout analysis have long been treated as two separate
tasks in different image domains. In this paper, we bring them together and introduce the …

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 …

This paper presents MOAT, a family of neural networks that build on top of MObile
convolution (ie, inverted residual blocks) and ATtention. Unlike the current works that stack …

Abstract We present TubeFormer-DeepLab, the first attempt to tackle multiple core video
segmentation tasks in a unified manner. Different video segmentation tasks (eg, video …

The globe and more particularly the economically developed regions of the world are
currently in the era of the Fourth Industrial Revolution (4IR). Conversely, the economically …

The rise of transformers in vision tasks not only advances network backbone designs, but
also starts a brand-new page to achieve end-to-end image recognition (eg., object detection …

Dense prediction tasks, such as semantic segmentation, depth estimation, and surface
normal prediction, can be easily formulated as per-pixel classification (discrete outputs) or …

Panoptic image segmentation is the computer vision task of finding groups of pixels in an
image and assigning semantic classes and object instance identifiers to them. Research in …