Recent years have witnessed enormous progress in AI-related fields such as computer
vision, machine learning, and autonomous vehicles. As with any rapidly growing field, it …

Semantic segmentation, also called scene labeling, refers to the process of assigning a
semantic label (eg car, people, and road) to each pixel of an image. It is an essential data …

Abstract We present Boundary IoU (Intersection-over-Union), a new segmentation
evaluation measure focused on boundary quality. We perform an extensive analysis across …

Abstract Recently, Neural Architecture Search (NAS) has successfully identified neural
network architectures that exceed human designed ones on large-scale image …

RGB-D semantic segmentation has attracted increasing attention over the past few years.
Existing methods mostly employ homogeneous convolution operators to consume the RGB …

Spatial pyramid pooling module or encode-decoder structure are used in deep neural
networks for semantic segmentation task. The former networks are able to encode multi …

In this work, we revisit atrous convolution, a powerful tool to explicitly adjust filter's field-of-
view as well as control the resolution of feature responses computed by Deep Convolutional …

Image semantic segmentation has received great attention in computer vision, whose aim is
to segment different objects and provide them different semantic category labels so that the …

Semantic classes can be either things (objects with a well-defined shape, eg car, person) or
stuff (amorphous background regions, eg grass, sky). While lots of classification and …

The design of neural network architectures is an important component for achieving state-of-
the-art performance with machine learning systems across a broad array of tasks. Much …