Related papers: Enhancing Geometric Factors in Model Learning and …
Bounding box regression is the crucial step in object detection. In existing methods, while $\ell_n$-norm loss is widely adopted for bounding box regression, it is not tailored to the evaluation metric, i.e., Intersection over Union (IoU).…
We demonstrate that many detection methods are designed to identify only a sufficently accurate bounding box, rather than the best available one. To address this issue we propose a simple and fast modification to the existing methods called…
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…
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)…
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…
Confluence is a novel non-Intersection over Union (IoU) alternative to Non-Maxima Suppression (NMS) in bounding box post-processing in object detection. It overcomes the inherent limitations of IoU-based NMS variants to provide a more…
Non-maximum suppression (NMS) is widely used in object detection pipelines for removing duplicated bounding boxes. The inconsistency between the confidence for NMS and the real localization confidence seriously affects detection…
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…
The loss function for bounding box regression (BBR) is essential to object detection. Its good definition will bring significant performance improvement to the model. Most existing works assume that the examples in the training data are…
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…
In object detection, non-maximum suppression (NMS) methods are extensively adopted to remove horizontal duplicates of detected dense boxes for generating final object instances. However, due to the degraded quality of dense detection boxes…
Jointly integrating aspect ratio and context has been extensively studied and shown performance improvement in traditional object detection systems such as the DPMs. It, however, has been largely ignored in deep neural network based…
Object detection is an important part in the field of computer vision, and the effect of object detection is directly determined by the regression accuracy of the prediction box. As the key to model training, IoU (Intersection over Union)…
With the rapid development of detectors, Bounding Box Regression (BBR) loss function has constantly updated and optimized. However, the existing IoU-based BBR still focus on accelerating convergence by adding new loss terms, ignoring the…
It has been a long history that most object detection methods obtain objects by using the non-maximum suppression (NMS) and its improved versions like Soft-NMS to remove redundant bounding boxes. We challenge those NMS-based methods from…
Object detection has seen remarkable progress in recent years with the introduction of Convolutional Neural Networks (CNN). Object detection is a multi-task learning problem where both the position of the objects in the images as well as…
Bounding box regression is one of the important steps of object detection. However, rotation detectors often involve a more complicated loss based on SkewIoU which is unfriendly to gradient-based training. Most of the existing loss…
Four-variable-independent-regression localization losses, such as Smooth-$\ell_1$ Loss, are used by default in modern detectors. Nevertheless, this kind of loss is oversimplified so that it is inconsistent with the final evaluation metric,…
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…
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…