One-to-one set matching is a key design for DETR to establish its end-to-end capability, so
that object detection does not require a hand-crafted NMS (non-maximum suppression) to …

Hospitals, especially their emergency services, receive a high number of wrist fracture
cases. For correct diagnosis and proper treatment of these, images obtained from various …

Abstract We propose Rank & Sort (RS) Loss, a ranking-based loss function to train deep
object detection and instance segmentation methods (ie visual detectors). RS Loss …

Automated driving requires reliable perception of the environment to ensure the safety of the
driving task. One common perception task is 3D object detection, which aims at perceiving …

Reliable usage of object detectors require them to be calibrated—a crucial problem that
requires careful attention. Recent approaches towards this involve (1) designing new loss …

Power quality (PQ) problems, including voltage sag, flicker, and harmonics, are the main
concerns for the grid operator. Among these disturbances, voltage sag, which affects the …

The current approach for testing the robustness of object detectors suffers from serious
deficiencies such as improper methods of performing out-of-distribution detection and using …

As computer vision technologies undergo extensive advancement in recent years, the
significance of object detection has been valued to an unprecedented level in a variety of …

Medical image segmentation has long been a compelling and fundamental problem in the
realm of neuroscience. This is an extremely challenging task due to the intensely interfering …

In intelligent building management, knowing the number of people and their location in a
room are important for better control of its illumination, ventilation, and heating with reduced …