With the rapid development of deep learning techniques, deep convolutional neural
networks (DCNNs) have become more important for object detection. Compared with …

Deep learning models are widely being employed for object detection due to their high
performance. However, the majority of applications that require object detection are …

In this work, we design a simple, direct, and fast framework for instance segmentation with
strong performance. To this end, we propose a novel and effective approach, termed …

Compared to many other dense prediction tasks, eg, semantic segmentation, it is the
arbitrary number of instances that has made instance segmentation much more challenging …

Aiming at the problems of low detection accuracy and inaccurate positioning accuracy of
light-weight network in traffic sign recognition task, an improved light-weight traffic sign …

LiDAR-based 3D detection plays a vital role in autonomous navigation. Surprisingly,
although autonomous vehicles (AVs) must detect both near-field objects (for collision …

Object detection is one of the most challenging tasks in computer vision. With the advances
in semiconductor devices and chip technology, hardware accelerators have been widely …

Confluence is a novel non-Intersection over Union (IoU) alternative to Non-Maxima
Suppression (NMS) in bounding box post-processing in object detection. It overcomes the …

Computer vision models are currently making great strides in object detection with the rapid
development of deep convolutional detectors. However, generating a large number of …

This paper proposes anchor pruning for object detection in one-stage anchor-based
detectors. While pruning techniques are widely used to reduce the computational cost of …