Recent advances in deep learning have shown excellent performance in various scene
understanding tasks. However, in some complex environments or under challenging …

We present a simple yet effective fully convolutional one-stage 3D object detector for LiDAR
point clouds of autonomous driving scenes, termed FCOS-LiDAR. Unlike the dominant …

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 …

We propose a simple yet effective instance segmentation framework, termed CondInst
(conditional convolutions for instance segmentation). Top-performing instance segmentation …

Spatial pooling has been proven highly effective to capture long-range contextual
information for pixel-wise prediction tasks, such as scene parsing. In this paper, beyond …

In computer vision, object detection is one of most important tasks, which underpins a few
instance-level recognition tasks and many downstream applications. Recently one-stage …

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

Monocular depth prediction plays a crucial role in understanding 3D scene geometry.
Although recent methods have achieved impressive progress in evaluation metrics such as …

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 …

In this work, we study the continual semantic segmentation problem, where the deep neural
networks are required to incorporate new classes continually without catastrophic forgetting …