English
Related papers

Related papers: IoU-aware Single-stage Object Detector for Accurat…

200 papers

Single-stage object detectors have been widely applied in computer vision applications due to their high efficiency. However, we find that the loss functions adopted by single-stage object detectors hurt the localization accuracy seriously.…

Computer Vision and Pattern Recognition · Computer Science 2020-12-15 Shengkai Wu , Jinrong Yang , Xinggang Wang , Xiaoping Li

Existing single-stage detectors for locating objects in point clouds often treat object localization and category classification as separate tasks, so the localization accuracy and classification confidence may not well align. To address…

Computer Vision and Pattern Recognition · Computer Science 2020-12-08 Wu Zheng , Weiliang Tang , Sijin Chen , Li Jiang , Chi-Wing Fu

Current anchor-free object detectors are quite simple and effective yet lack accurate label assignment methods, which limits their potential in competing with classic anchor-based models that are supported by well-designed assignment…

Computer Vision and Pattern Recognition · Computer Science 2021-04-30 Jiachen Li , Bowen Cheng , Rogerio Feris , Jinjun Xiong , Thomas S. Huang , Wen-Mei Hwu , Humphrey Shi

Accurately ranking the vast number of candidate detections is crucial for dense object detectors to achieve high performance. Prior work uses the classification score or a combination of classification and predicted localization scores to…

Computer Vision and Pattern Recognition · Computer Science 2021-03-05 Haoyang Zhang , Ying Wang , Feras Dayoub , Niko Sünderhauf

Since Intersection-over-Union (IoU) based optimization maintains the consistency of the final IoU prediction metric and losses, it has been widely used in both regression and classification branches of single-stage 2D object detectors.…

Computer Vision and Pattern Recognition · Computer Science 2022-07-21 Hualian Sheng , Sijia Cai , Na Zhao , Bing Deng , Jianqiang Huang , Xian-Sheng Hua , Min-Jian Zhao , Gim Hee Lee

RetinaNet proposed Focal Loss for classification task and improved one-stage detectors greatly. However, there is still a gap between it and two-stage detectors. We analyze the prediction of RetinaNet and find that the misalignment of…

Computer Vision and Pattern Recognition · Computer Science 2020-11-23 Wu Kehe , Chen Zuge , Zhang Xiaoliang , Li Wei

There are still two problems in SDD causing some inaccurate results: (1) In the process of feature extraction, with the layer-by-layer acquisition of semantic information, local information is gradually lost, resulting into less…

Computer Vision and Pattern Recognition · Computer Science 2022-10-11 Aisha Chandio , Gong Gui , Teerath Kumar , Irfan Ullah , Ramin Ranjbarzadeh , Arunabha M Roy , Akhtar Hussain , Yao Shen

Previous single-stage detectors typically suffer the misalignment between localization accuracy and classification confidence. To solve the misalignment problem, we introduce a novel rectification method named neighbor IoU-voting (NIV)…

Computer Vision and Pattern Recognition · Computer Science 2024-01-24 Shuai Liu , Di Wang , Quan Wang , Kai Huang

One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Kean Chen , Jianguo Li , Weiyao Lin , John See , Ji Wang , Lingyu Duan , Zhibo Chen , Changwei He , Junni Zou

The detection of 3D objects through a single perspective camera is a challenging issue. The anchor-free and keypoint-based models receive increasing attention recently due to their effectiveness and simplicity. However, most of these…

Computer Vision and Pattern Recognition · Computer Science 2022-04-26 Wei Chen , Jie Zhao , Wan-Lei Zhao , Song-Yuan Wu

Localization Quality Estimation (LQE) helps to improve detection performance as it benefits post processing through jointly considering classification score and localization accuracy. In this perspective, for further leveraging the close…

Computer Vision and Pattern Recognition · Computer Science 2023-09-26 Pengfei Liu , Weibo Wang , Yuhan Guo , Jiubin Tan

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)…

Computer Vision and Pattern Recognition · Computer Science 2024-08-14 Xiangjie Luo , Zhihao Cai , Bo Shao , Yingxun Wang

Most deep learning object detectors are based on the anchor mechanism and resort to the Intersection over Union (IoU) between predefined anchor boxes and ground truth boxes to evaluate the matching quality between anchors and objects. In…

Computer Vision and Pattern Recognition · Computer Science 2020-09-30 Heng Zhang , Elisa Fromont , Sébastien Lefevre , Bruno Avignon

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

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…

Computer Vision and Pattern Recognition · Computer Science 2021-08-26 Keyang Wang , Lei Zhang , Wenli Song , Qinghai Lang , Lingyun Qin

One-stage object detection is commonly implemented by optimizing two sub-tasks: object classification and localization, using heads with two parallel branches, which might lead to a certain level of spatial misalignment in predictions…

Computer Vision and Pattern Recognition · Computer Science 2021-08-31 Chengjian Feng , Yujie Zhong , Yu Gao , Matthew R. Scott , Weilin Huang

The localization quality of automatic object detectors is typically evaluated by the Intersection over Union (IoU) score. In this work, we show that humans have a different view on localization quality. To evaluate this, we conduct a survey…

Computer Vision and Pattern Recognition · Computer Science 2022-07-29 Ombretta Strafforello , Vanathi Rajasekart , Osman S. Kayhan , Oana Inel , Jan van Gemert

There are mainly two types of state-of-the-art object detectors. On one hand, we have two-stage detectors, such as Faster R-CNN (Region-based Convolutional Neural Networks) or Mask R-CNN, that (i) use a Region Proposal Network to generate…

Computer Vision and Pattern Recognition · Computer Science 2018-09-03 Petru Soviany , Radu Tudor Ionescu

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…

Computer Vision and Pattern Recognition · Computer Science 2018-08-01 Borui Jiang , Ruixuan Luo , Jiayuan Mao , Tete Xiao , Yuning Jiang

Modern oriented object detectors typically predict a set of bounding boxes and select the top-ranked ones based on estimated localization quality. Achieving high detection performance requires that the estimated quality closely aligns with…

Computer Vision and Pattern Recognition · Computer Science 2025-11-12 Yunhui Zhu , Buliao Huang
‹ Prev 1 2 3 10 Next ›