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 …

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 …

Recent years have witnessed the remarkable developments made by deep learning
techniques for object detection, a fundamentally challenging problem of computer vision …

Automatic ship detection in high-resolution remote sensing images has attracted increasing
research interest due to its numerous practical applications. However, there still exist …

Class Imbalance and scales imbalance are common in object detection. A class imbalance
occurs due to insufficient inequality between the number of instances with respect to …

As a widely used vital sign within cardiology, Electrocardiography (ECG) provides the basis
for assessing heart function and diagnosing cardiovascular diseases. Automated anomaly …

Localization is an essential part of object detection, which is usually accomplished by
bounding box regression guided by ℓ n-norm-based or IoU-based loss functions, where IoU …

冷却塔排放容易造成大气污染, 利用高分辨率遥感影像对冷却塔进行检测, 可以为废气排放治理
提供决策数据. 针对传统算法在高分辨率遥感影像目标检测中检测精度不高, 检测速度慢等问题 …

Object detection becomes challenging due to feature unbalancing, less contextual
information and class imbalance. The feature pyramid has been used to learn multiscale …

Training process is crucial to the success of object detectors. Real-world datasets often have
skewed distributions, which results in imbalance issues during the training process, and thus …