English
Related papers

Related papers: Pseudo-IoU: Improving Label Assignment in Anchor-F…

200 papers

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.…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Milad Khanchi , Maria Amer , Charalambos Poullis

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

Object detection has made tremendous strides in computer vision. Small object detection with appearance degradation is a prominent challenge, especially for aerial observations. To collect sufficient positive/negative samples for heuristic…

Computer Vision and Pattern Recognition · Computer Science 2022-05-04 Dong Liang , Qixiang Geng , Zongqi Wei , Dmitry A. Vorontsov , Ekaterina L. Kim , Mingqiang Wei , Huiyu Zhou

Great labels make great models. However, traditional labeling approaches for tasks like object detection have substantial costs at scale. Furthermore, alternatives to fully-supervised object detection either lose functionality or require…

Computer Vision and Pattern Recognition · Computer Science 2025-06-04 Brent A. Griffin , Manushree Gangwar , Jacob Sela , Jason J. Corso

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

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

Occlusion presents a significant challenge for safety-critical applications such as autonomous driving. Collaborative perception has recently attracted a large research interest thanks to the ability to enhance the perception of autonomous…

Computer Vision and Pattern Recognition · Computer Science 2024-04-10 Minh-Quan Dao , Holger Caesar , Julie Stephany Berrio , Mao Shan , Stewart Worrall , Vincent Frémont , Ezio Malis

Unsupervised 3D object detection methods have emerged to leverage vast amounts of data without requiring manual labels for training. Recent approaches rely on dynamic objects for learning to detect mobile objects but penalize the detections…

Computer Vision and Pattern Recognition · Computer Science 2025-02-20 Ted Lentsch , Holger Caesar , Dariu M. Gavrila

Semi-Supervised Object Detection (SSOD) has been successful in improving the performance of both R-CNN series and anchor-free detectors. However, one-stage anchor-based detectors lack the structure to generate high-quality or flexible…

Computer Vision and Pattern Recognition · Computer Science 2023-03-15 Bowen Xu , Mingtao Chen , Wenlong Guan , Lulu Hu

Recently, significant progress has been made in the research of 3D object detection. However, most prior studies have focused on the utilization of center-based or anchor-based label assignment schemes. Alternative label assignment…

Computer Vision and Pattern Recognition · Computer Science 2024-05-24 Shuai Liu , Boyang Li , Zhiyu Fang , Kai Huang

Multi-modal methods based on camera and LiDAR sensors have garnered significant attention in the field of 3D detection. However, many prevalent works focus on single or partial stage fusion, leading to insufficient feature extraction and…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Zhiwei Ning , Zhaojiang Liu , Xuanang Gao , Yifan Zuo , Jie Yang , Yuming Fang , Wei Liu

Anchor-based Siamese trackers have achieved remarkable advancements in accuracy, yet the further improvement is restricted by the lagged tracking robustness. We find the underlying reason is that the regression network in anchor-based…

Computer Vision and Pattern Recognition · Computer Science 2020-07-10 Zhipeng Zhang , Houwen Peng , Jianlong Fu , Bing Li , Weiming Hu

Traversability estimation is critical for enabling robots to navigate across diverse terrains and environments. While recent self-supervised learning methods achieve promising results, they often fail to capture the characteristics of…

Robotics · Computer Science 2025-08-26 Zipeng Fang , Yanbo Wang , Lei Zhao , Weidong Chen

Anchor-based detectors have been continuously developed for object detection. However, the individual anchor box makes it difficult to predict the boundary's offset accurately. Instead of taking each bounding box as a closed individual, we…

Computer Vision and Pattern Recognition · Computer Science 2023-10-10 Yilong Lv , Min Li , Yujie He , Shaopeng Li , Zhuzhen He , Aitao Yang

Bounding box regression (BBR) is fundamental to object detection, where the regression loss is crucial for accurate localization. Existing IoU-based losses often incorporate handcrafted geometric penalties to address IoU's…

Computer Vision and Pattern Recognition · Computer Science 2025-09-01 Haoyuan Liu , Hiroshi Watanabe

Traditional object detection models are constrained by the limitations of closed-set datasets, detecting only categories encountered during training. While multimodal models have extended category recognition by aligning text and image…

Computer Vision and Pattern Recognition · Computer Science 2024-12-31 Lihao Liu , Juexiao Feng , Hui Chen , Ao Wang , Lin Song , Jungong Han , Guiguang Ding

Despite its significant success, object detection in traffic and transportation scenarios requires time-consuming and laborious efforts in acquiring high-quality labeled data. Therefore, Unsupervised Domain Adaptation (UDA) for object…

Computer Vision and Pattern Recognition · Computer Science 2025-07-02 Zehua Fu , Chenguang Liu , Yuyu Chen , Jiaqi Zhou , Qingjie Liu , Yunhong Wang

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

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…

Computer Vision and Pattern Recognition · Computer Science 2023-04-11 Zanjia Tong , Yuhang Chen , Zewei Xu , Rong Yu

Existing Multiple Object Tracking (MOT) methods design complex architectures for better tracking performance. However, without a proper organization of input information, they still fail to perform tracking robustly and suffer from frequent…

Computer Vision and Pattern Recognition · Computer Science 2022-12-07 Bisheng Wang , Horst Possegger , Horst Bischof , Guo Cao