English
Related papers

Related papers: Focaler-IoU: More Focused Intersection over Union …

200 papers

Label assignment plays a significant role in modern object detection models. Detection models may yield totally different performances with different label assignment strategies. For anchor-based detection models, the IoU (Intersection over…

Computer Vision and Pattern Recognition · Computer Science 2022-09-20 Tianxiao Zhang , Bo Luo , Ajay Sharda , Guanghui Wang

Bounding box regression (BBR) has been widely used in object detection and instance segmentation, which is an important step in object localization. However, most of the existing loss functions for bounding box regression cannot be…

Computer Vision and Pattern Recognition · Computer Science 2024-05-17 Siliang Ma , Yong Xu

The CenterTrack tracking algorithm achieves state-of-the-art tracking performance using a simple detection model and single-frame spatial offsets to localize objects and predict their associations in a single network. However, this joint…

Computer Vision and Pattern Recognition · Computer Science 2021-05-18 Nanyang Yang , Yi Wang , Lap-Pui Chau

Bounding boxes uniquely characterize object detection, where a good detector gives accurate bounding boxes of categories of interest. However, in the real-world where test ground truths are not provided, it is non-trivial to find out…

Computer Vision and Pattern Recognition · Computer Science 2024-03-21 Yang Yang , Wenhai Wang , Zhe Chen , Jifeng Dai , Liang Zheng

Accurate pedestrian classification and localization have received considerable attention due to their wide applications such as security monitoring, autonomous driving, etc. Although pedestrian detectors have made great progress in recent…

Computer Vision and Pattern Recognition · Computer Science 2021-03-19 Yan Luo , Chongyang Zhang , Muming Zhao , Hao Zhou , Jun Sun

Locating an object in a sequence of frames, given its appearance in the first frame of the sequence, is a hard problem that involves many stages. Usually, state-of-the-art methods focus on bringing novel ideas in the visual encoding or…

Computer Vision and Pattern Recognition · Computer Science 2024-05-20 Omar Abdelaziz , Mohamed Sami Shehata

Training a robust classifier and an accurate box regressor are difficult for occluded pedestrian detection. Traditionally adopted Intersection over Union (IoU) measurement does not consider the occluded region of the object and leads to…

Computer Vision and Pattern Recognition · Computer Science 2019-11-27 Ruiqi Lu , Huimin Ma

Existing detection methods commonly use a parameterized bounding box (BBox) to model and detect (horizontal) objects and an additional rotation angle parameter is used for rotated objects. We argue that such a mechanism has fundamental…

Computer Vision and Pattern Recognition · Computer Science 2022-09-23 Xue Yang , Gefan Zhang , Xiaojiang Yang , Yue Zhou , Wentao Wang , Jin Tang , Tao He , Junchi Yan

Few-shot object detection has gained significant attention in recent years as it has the potential to greatly reduce the reliance on large amounts of manually annotated bounding boxes. While most existing few-shot object detection…

Computer Vision and Pattern Recognition · Computer Science 2022-04-25 Sueyeon Kim , Woo-Jeoung Nam , Seong-Whan Lee

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,…

Computer Vision and Pattern Recognition · Computer Science 2021-12-06 Hanyang Peng , Shiqi Yu

Effective feature fusion of multispectral images plays a crucial role in multi-spectral object detection. Previous studies have demonstrated the effectiveness of feature fusion using convolutional neural networks, but these methods are…

Computer Vision and Pattern Recognition · Computer Science 2023-08-16 Jifeng Shen , Yifei Chen , Yue Liu , Xin Zuo , Heng Fan , Wankou Yang

Inadequate bounding box modeling in regression tasks constrains the performance of one-stage 3D object detection. Our study reveals that the primary reason lies in two aspects: (1) The limited center-offset prediction seriously impairs the…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Weiping Xiao , Yiqiang Wu , Chang Liu , Yu Qin , Xiaomao Li , Liming Xin

Two-stage deep object detectors generate a set of regions-of-interest (RoI) in the first stage, then, in the second stage, identify objects among the proposed RoIs that sufficiently overlap with a ground truth (GT) box. The second stage is…

Computer Vision and Pattern Recognition · Computer Science 2020-06-22 Kemal Oksuz , Baris Can Cam , Emre Akbas , Sinan Kalkan

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…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Xinxuan Lu , Derek Gloudemans , Shepard Xia , Daniel B. Work

Most object detection methods use bounding boxes to encode and represent the object shape and location. In this work, we explore a fuzzy representation of object regions using Gaussian distributions, which provides an implicit binary…

Computer Vision and Pattern Recognition · Computer Science 2024-03-27 Jeffri M. Llerena , Luis Felipe Zeni , Lucas N. Kristen , Claudio Jung

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…

Computer Vision and Pattern Recognition · Computer Science 2021-08-30 Keyang Wang , Lei Zhang

Without densely tiled anchor boxes or grid points in the image, sparse R-CNN achieves promising results through a set of object queries and proposal boxes updated in the cascaded training manner. However, due to the sparse nature and the…

Computer Vision and Pattern Recognition · Computer Science 2022-10-06 Jing Zhao , Shengjian Wu , Li Sun , Qingli Li

Region sampling or weighting is significantly important to the success of modern region-based object detectors. Unlike some previous works, which only focus on "hard" samples when optimizing the objective function, we argue that sample…

Computer Vision and Pattern Recognition · Computer Science 2020-06-16 Qi Cai , Yingwei Pan , Yu Wang , Jingen Liu , Ting Yao , Tao Mei

Bounding boxes are often used to communicate automatic object detection results to humans, aiding humans in a multitude of tasks. We investigate the relationship between bounding box localization errors and human task performance. We use…

Computer Vision and Pattern Recognition · Computer Science 2024-02-01 Sven de Witte , Ombretta Strafforello , Jan van Gemert

Cross-domain object detection is more challenging than object classification since multiple objects exist in an image and the location of each object is unknown in the unlabeled target domain. As a result, when we adapt features of…

Computer Vision and Pattern Recognition · Computer Science 2022-05-10 Junguang Jiang , Baixu Chen , Jianmin Wang , Mingsheng Long