The machine learning community has been overwhelmed by a plethora of deep learning--
based approaches. Many challenging computer vision tasks, such as detection, localization …

Semantic image segmentation, which becomes one of the key applications in image
processing and computer vision domain, has been used in multiple domains such as …

Current state-of-the-art methods for image segmentation form a dense image representation
where the color, shape and texture information are all processed together inside a deep …

Cascade is a classic yet powerful architecture that has boosted performance on various
tasks. However, how to introduce cascade to instance segmentation remains an open …

Full-image dependencies provide useful contextual information to benefit visual
understanding problems. In this work, we propose a Criss-Cross Network (CCNet) for …

In this paper, we address the scene segmentation task by capturing rich contextual
dependencies based on the self-attention mechanism. Unlike previous works that capture …

Feature upsampling is a key operation in a number of modern convolutional network
architectures, eg feature pyramids. Its design is critical for dense prediction tasks such as …

In this paper, we propose a unified panoptic segmentation network (UPSNet) for tackling the
newly proposed panoptic segmentation task. On top of a single backbone residual network …

Recent studies witnessed that context features can significantly improve the performance of
deep semantic segmentation networks. Current context based segmentation methods differ …

Recent works have made great progress in semantic segmentation by exploiting richer
context, most of which are designed from a spatial perspective. In contrast to previous works …