The advancements in machine learning (ML) opened a new opportunity to bring intelligence
to the low-end Internet-of-Things (IoT) nodes, such as microcontrollers. Conventional ML …

The emerging field of artificial intelligence of things (AIoT, AI+ IoT) is driven by the
widespread use of intelligent infrastructures and the impressive success of deep learning …

Batch normalization is a key component of most image classification models, but it has many
undesirable properties stemming from its dependence on the batch size and interactions …

We present a new method for efficient high-quality image segmentation of objects and
scenes. By analogizing classical computer graphics methods for efficient rendering with over …

In this paper, we study the context aggregation problem in semantic segmentation.
Motivated by that the label of a pixel is the category of the object that the pixel belongs to, we …

The success of monocular depth estimation relies on large and diverse training sets. Due to
the challenges associated with acquiring dense ground-truth depth across different …

In this paper, we address the semantic segmentation task with a new context aggregation
scheme named object context, which focuses on enhancing the role of object information …

The recently introduced panoptic segmentation task has renewed our community's interest
in unifying the tasks of instance segmentation (for thing classes) and semantic segmentation …

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

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