Neural Architecture Search (NAS) methods have been growing in popularity. These
techniques have been fundamental to automate and speed up the time consuming and error …

Neural architecture search (NAS) has attracted increasing attention. In recent years,
individual search methods have been replaced by weight-sharing search methods for higher …

Abstract We present MaX-DeepLab, the first end-to-end model for panoptic segmentation.
Our approach simplifies the current pipeline that depends heavily on surrogate sub-tasks …

Convolution exploits locality for efficiency at a cost of missing long range context. Self-
attention has been adopted to augment CNNs with non-local interactions. Recent works …

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

The past year has witnessed the rapid development of applying the Transformer module to
vision problems. While some researchers have demonstrated that Transformer-based …

Abstract We propose Mask Guided (MG) Matting, a robust matting framework that takes a
general coarse mask as guidance. MG Matting leverages a network (PRN) design which …

Deep neural networks (DNNs) are vulnerable to adversarial noises, which motivates the
benchmark of model robustness. Existing benchmarks mainly focus on evaluating defenses …

Neural architecture search (NAS) has emerged as a promising avenue for automatically
designing task-specific neural networks. Existing NAS approaches require one complete …

Multiple object tracking and segmentation requires detecting, tracking, and segmenting
objects belonging to a set of given classes. Most approaches only exploit the temporal …