In computer vision, significant advances have been made on object detection with the rapid
development of deep convolutional neural networks (CNN). This paper provides a …

Abstract Deep Neural Networks (DNNs) learn representation from data with an impressive
capability, and brought important breakthroughs for processing images, time-series, natural …

Traditional camera sensors rely on human eyes for observation. However, human eyes are
prone to fatigue when observing objects of different sizes for a long time in complex scenes …

One-stage object detection is commonly implemented by optimizing two sub-tasks: object
classification and localization, using heads with two parallel branches, which might lead to a …

False negatives (FN) in 3D object detection, eg, missing predictions of pedestrians, vehicles,
or other obstacles, can lead to potentially dangerous situations in autonomous driving. While …

Accurately ranking the vast number of candidate detections is crucial for dense object
detectors to achieve high performance. Prior work uses the classification score or a …

One-stage detector basically formulates object detection as dense classification and
localization (ie, bounding box regression). The classification is usually optimized by Focal …

Complicated underwater environments bring new challenges to object detection, such as
unbalanced light conditions, low contrast, occlusion, and mimicry of aquatic organisms …

Object detection is a fundamental computer vision task that simultaneously predicts the
category and localization of the targets of interest. Recently one-stage (also termed “dense”) …

In this paper, we present a comprehensive review of the imbalance problems in object
detection. To analyze the problems in a systematic manner, we introduce a problem-based …