Deep learning object detection methods are usually based on anchor-free or anchor-based scheme for extracting proposals and one-stage two-stage structure producing final predictions. As each has its own strength weakness, combining their in a unified framework is an interesting research topic. However, this topic not attracted much attention recent years. This paper presents method that utilize...

Accurate and fast 3D object detection from point clouds is a key task in autonomous driving. Existing one-stage methods can achieve real-time performance, however, they are dominated by anchor-based detectors which inefficient require additional post-processing. In this paper, we eliminate anchors model an as single point—the center of its bounding box. Based on the point, propose anchor-free C...

Rotated object detection in aerial images is still challenging due to arbitrary orientations, large scale and aspect ratio variations, extreme density of objects. Existing state-of-the-art rotated methods mainly rely on angle-based detectors. However, detectors can easily suffer from a long-standing boundary problem. To tackle this problem, we propose purely angle-free framework for detection, ...

Oriented object detection is a challenging task in scene text and remote sensing image analysis, it has attracted extensive attention due to the development of deep learning recent years. Currently, mainstream oriented detectors are anchor-based methods. These methods increase computational load network cause large amount anchor box redundancy. In order address this issue, we proposed an anchor...

Vision-based object detection is an essential component of autonomous driving. Because vehicles typically have limited on-board computing resources, a small-sized model required. Simultaneously, high accuracy and real-time inference speeds are required to ensure safety while In this paper, anchor-free lightweight detector for driving called ALODAD proposed. incorporates attention scheme into th...