English
Related papers

Related papers: Reconcile Prediction Consistency for Balanced Obje…

200 papers

Object detectors are conventionally trained by a weighted sum of classification and localization losses. Recent studies (e.g., predicting IoU with an auxiliary head, Generalized Focal Loss, Rank & Sort Loss) have shown that forcing these…

Computer Vision and Pattern Recognition · Computer Science 2023-01-04 Fehmi Kahraman , Kemal Oksuz , Sinan Kalkan , Emre Akbas

Object detection involves two sub-tasks, i.e. localizing objects in an image and classifying them into various categories. For existing CNN-based detectors, we notice the widespread divergence between localization and classification, which…

Computer Vision and Pattern Recognition · Computer Science 2021-03-26 Taiheng Zhang , Qiaoyong Zhong , Shiliang Pu , Di Xie

Loss functions is a crucial factor that affecting the detection precision in object detection task. In this paper, we optimize both two loss functions for classification and localization simultaneously. Firstly, by multiplying an IoU-based…

Computer Vision and Pattern Recognition · Computer Science 2021-08-02 Shang Jiang , Haoran Qin , Bingli Zhang , Jieyu Zheng

Task inharmony problem commonly occurs in modern object detectors, leading to inconsistent qualities between classification and regression tasks. The predicted boxes with high classification scores but poor localization positions or low…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Long Huang , Zhiwei Dong , Song-Lu Chen , Ruiyao Zhang , Shutong Ti , Feng Chen , Xu-Cheng Yin

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 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…

Computer Vision and Pattern Recognition · Computer Science 2022-05-26 Zhora Gevorgyan

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

Compared with model architectures, the training process, which is also crucial to the success of detectors, has received relatively less attention in object detection. In this work, we carefully revisit the standard training practice of…

Computer Vision and Pattern Recognition · Computer Science 2019-04-05 Jiangmiao Pang , Kai Chen , Jianping Shi , Huajun Feng , Wanli Ouyang , Dahua Lin

Most existing object detectors suffer from class imbalance problems that hinder balanced performance. In particular, anchor free object detectors have to solve the background imbalance problem due to detection in a per-pixel prediction…

Computer Vision and Pattern Recognition · Computer Science 2020-12-29 Hopyong Gil , Sangwoo Park , Yusang Park , Wongoo Han , Juyean Hong , Juneyoung Jung

State-of-the-art object detectors rely on regressing and classifying an extensive list of possible anchors, which are divided into positive and negative samples based on their intersection-over-union (IoU) with corresponding groundtruth…

Computer Vision and Pattern Recognition · Computer Science 2020-06-01 Hengduo Li , Zuxuan Wu , Chen Zhu , Caiming Xiong , Richard Socher , Larry S. Davis

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

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

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…

Computer Vision and Pattern Recognition · Computer Science 2024-01-22 Hao Zhang , Shuaijie Zhang

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…

Computer Vision and Pattern Recognition · Computer Science 2022-04-27 Tu Zheng , Shuai Zhao , Yang Liu , Zili Liu , Deng Cai

Arbitrary-oriented object detection is a relatively emerging but challenging task. Although remarkable progress has been made, there still remain many unsolved issues due to the large diversity of patterns in orientation, scale, aspect…

Computer Vision and Pattern Recognition · Computer Science 2023-07-11 Peng Sun , Yongbin Zheng , Wenqi Wu , Wanying Xu , Shengjian Bai

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…

Computer Vision and Pattern Recognition · Computer Science 2022-07-19 Yi-Fan Zhang , Weiqiang Ren , Zhang Zhang , Zhen Jia , Liang Wang , Tieniu Tan

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 , Weiyao Lin , Jianguo Li , John See , Ji Wang , Junni Zou

Edge computing-based 3D perception has received attention in intelligent transportation systems (ITS) because real-time monitoring of traffic candidates potentially strengthens Vehicle-to-Everything (V2X) orchestration. Thanks to the…

Computer Vision and Pattern Recognition · Computer Science 2022-11-15 Haolin Zhang , M S Mekala , Zulkar Nain , Dongfang Yang , Ju H. Park , Ho-Youl Jung

While fine-tuning pre-trained models for downstream classification is the conventional paradigm in NLP, often task-specific nuances may not get captured in the resultant models. Specifically, for tasks that take two inputs and require the…

Computation and Language · Computer Science 2022-03-28 Ashutosh Kumar , Aditya Joshi

With the continuous improvement of the performance of object detectors via advanced model architectures, imbalance problems in the training process have received more attention. It is a common paradigm in object detection frameworks to…

Computer Vision and Pattern Recognition · Computer Science 2021-08-10 Yihao Luo , Xiang Cao , Juntao Zhang , Peng Cheng , Tianjiang Wang , Qi Feng
‹ Prev 1 2 3 10 Next ›