Related papers: Gaussian Guided IoU: A Better Metric for Balanced …
Recently Deep Learning based Siamese Networks with region proposals for visual object tracking becoming more popular. These networks, while testing, perform extra computations on output if trained network, to predict the bounding box. This…
This paper presents Mask-aware Intersection-over-Union (maIoU) for assigning anchor boxes as positives and negatives during training of instance segmentation methods. Unlike conventional IoU or its variants, which only considers the…
In object detection, determining which anchors to assign as positive or negative samples, known as anchor assignment, has been revealed as a core procedure that can significantly affect a model's performance. In this paper we propose a…
The effectiveness of Object Detection, one of the central problems in computer vision tasks, highly depends on the definition of the loss function - a measure of how accurately your ML model can predict the expected outcome. Conventional…
Modern CNN-based object detectors assign anchors for ground-truth objects under the restriction of object-anchor Intersection-over-Unit (IoU). In this study, we propose a learning-to-match approach to break IoU restriction, allowing objects…
Most existing point cloud based 3D object detectors focus on the tasks of classification and box regression. However, another bottleneck in this area is achieving an accurate detection confidence for the Non-Maximum Suppression (NMS)…
In object detection, bounding box regression (BBR) is a crucial step that determines the object localization performance. However, we find that most previous loss functions for BBR have two main drawbacks: (i) Both $\ell_n$-norm and…
Bounding box regression plays a crucial role in the field of object detection, and the positioning accuracy of object detection largely depends on the loss function of bounding box regression. Existing researchs improve regression…
Arbitrary-oriented objects widely appear in natural scenes, aerial photographs, remote sensing images, etc., thus arbitrary-oriented object detection has received considerable attention. Many current rotation detectors use plenty of anchors…
In Few-Shot Object Detection (FSOD), detecting small objects is extremely difficult. The limited supervision cripples the localization capabilities of the models and a few pixels shift can dramatically reduce the Intersection over Union…
Classification and regression are two pillars of object detectors. In most CNN-based detectors, these two pillars are optimized independently. Without direct interactions between them, the classification loss and the regression loss can not…
Bounding box regression is an important component in object detection. Recent work achieves promising performance by optimizing the Intersection over Union~(IoU). However, IoU-based loss has the gradient vanish problem in the case of low…
We focus on the construction of a loss function for the bounding box regression. The Intersection over Union (IoU) metric is improved to converge faster, to make the surface of the loss function smooth and continuous over the whole searched…
Optimizing the similarity between parametric shapes is crucial for numerous computer vision tasks, where Intersection over Union (IoU) stands as the canonical measure. However, existing optimization methods exhibit significant shortcomings:…
The anchor-based detectors handle the problem of scale variation by building the feature pyramid and directly setting different scales of anchors on each cell in different layers. However, it is difficult for box-wise anchors to guide the…
Oriented object detection has been developed rapidly in the past few years, where rotation equivariance is crucial for detectors to predict rotated boxes. It is expected that the prediction can maintain the corresponding rotation when…
Modern CNN-based object detectors rely on bounding box regression and non-maximum suppression to localize objects. While the probabilities for class labels naturally reflect classification confidence, localization confidence is absent. This…
As an important component of the detector localization branch, bounding box regression loss plays a significant role in object detection tasks. The existing bounding box regression methods usually consider the geometric relationship between…
Monocular 3D object detection is a challenging task because depth information is difficult to obtain from 2D images. A subset of viewpoint-agnostic monocular 3D detection methods also do not explicitly leverage scene homography or geometry…
In object detection, an intersection over union (IoU) threshold is required to define positives and negatives. An object detector, trained with low IoU threshold, e.g. 0.5, usually produces noisy detections. However, detection performance…