Related papers: Shape-IoU: More Accurate Metric considering Boundi…
Detecting oriented objects along with estimating their rotation information is one crucial step for analyzing remote sensing images. Despite that many methods proposed recently have achieved remarkable performance, most of them directly…
We propose a novel method for representing oriented objects in aerial images named Adaptive Period Embedding (APE). While traditional object detection methods represent object with horizontal bounding boxes, the objects in aerial images are…
Infrared small target detection still faces two persistent challenges: training instability from non-monotonic scale loss functions, and inadequate spatial attention due to generic convolution kernels that ignore the physical imaging…
Popular rotated detection methods usually use five parameters (coordinates of the central point, width, height, and rotation angle) to describe the rotated bounding box and l1-loss as the loss function. In this paper, we argue that the…
Weakly supervised oriented object detection (WS-OOD) has gained attention as a cost-effective alternative to fully supervised methods, providing both efficiency and high accuracy. Among weakly supervised approaches, horizontal bounding box…
Precision weak gravitational lensing experiments require measurements of galaxy shapes accurate to <1 part in 1000. We investigate measurement biases, noted by Voigt and Bridle (2009) and Melchior et al. (2009), that are common to shape…
In oriented object detection, current representations of oriented bounding boxes (OBBs) often suffer from boundary discontinuity problem. Methods of designing continuous regression losses do not essentially solve this problem. Although…
Current motion-based multiple object tracking (MOT) approaches rely heavily on Intersection-over-Union (IoU) for object association. Without using 3D features, they are ineffective in scenarios with occlusions or visually similar objects.…
In this work we study the impact of noise on the training of object detection networks for the medical domain, and how it can be mitigated by improving the training procedure. Annotating large medical datasets for training data-hungry deep…
Data augmentation has shown significant advancements in computer vision to improve model performance over the years, particularly in scenarios with limited and insufficient data. Currently, most studies focus on adjusting the image or its…
Object detection models perform well at localizing and classifying objects that they are shown during training. However, due to the difficulty and cost associated with creating and annotating detection datasets, trained models detect a…
Universal Lesion Detection (ULD) in computed tomography plays an essential role in computer-aided diagnosis. Promising ULD results have been reported by coarse-to-fine two-stage detection approaches, but such two-stage ULD methods still…
Weakly supervised object detection aims at learning precise object detectors, given image category labels. In recent prevailing works, this problem is generally formulated as a multiple instance learning module guided by an image…
Building segmentation is essential in infrastructure development, population management, and geological observations. This article targets shallow models due to their interpretable nature to assess the presence of LiDAR data for supervised…
In this paper, we consider the imperfection within machine learning-based 2D object detection and its impact on safety. We address a special sub-type of performance limitations: the prediction bounding box cannot be perfectly aligned with…
Occlusion handling is one of the challenges of object detection and segmentation, and scene understanding. Because objects appear differently when they are occluded in varying degree, angle, and locations. Therefore, determining the…
The accuracy of the 3D models created from medical scans depends on imaging hardware, segmentation methods and mesh processing techniques etc. The effects of geometry type, class imbalance, voxel and point cloud alignment on accuracy remain…
3D ultrasound (US) can facilitate detailed prenatal examinations for fetal growth monitoring. To analyze a 3D US volume, it is fundamental to identify anatomical landmarks of the evaluated organs accurately. Typical deep learning methods…
Instance segmentation of biological images is essential for studying object behaviors and properties. The challenges, such as clustering, occlusion, and adhesion problems of the objects, make instance segmentation a non-trivial task.…
Unsupervised 3D object detection aims to identify objects of interest from unlabeled raw data, such as LiDAR points. Recent approaches usually adopt pseudo 3D bounding boxes (3D bboxes) from clustering algorithm to initialize the model…