English
Related papers

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

200 papers

In Few-Shot Object Detection (FSOD), detecting small objects is extremely difficult. The limited supervision cripples the localization capabilities of the models and a few pixels shift can dramatically reduce the Intersection over Union…

Computer Vision and Pattern Recognition · Computer Science 2023-07-20 Pierre Le Jeune , Anissa Mokraoui

Many recent studies have shown that deep neural models are vulnerable to adversarial samples: images with imperceptible perturbations, for example, can fool image classifiers. In this paper, we present the first type-specific approach to…

Computer Vision and Pattern Recognition · Computer Science 2021-08-24 Omid Mohamad Nezami , Akshay Chaturvedi , Mark Dras , Utpal Garain

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…

Computer Vision and Pattern Recognition · Computer Science 2018-03-14 Lachlan Tychsen-Smith , Lars Petersson

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…

Computer Vision and Pattern Recognition · Computer Science 2022-02-03 Yan Gao , Qimeng Wang , Xu Tang , Haochen Wang , Fei Ding , Jing Li , Yao Hu

In object detection, an intersection over union (IoU) threshold is required to define positives and negatives. An object detector, trained with low IoU threshold, e.g. 0.5, usually produces noisy detections. However, detection performance…

Computer Vision and Pattern Recognition · Computer Science 2017-12-05 Zhaowei Cai , Nuno Vasconcelos

In this paper, we introduce an innovative method to improve the convergence speed and accuracy of object detection neural networks. Our approach, CONVERGE-FAST-AUXNET, is based on employing multiple, dependent loss metrics and weighting…

Computer Vision and Pattern Recognition · Computer Science 2018-08-15 Benjamin Schnieders , Karl Tuyls

General-purpose object-detection algorithms often dismiss the fine structure of detected objects. This can be traced back to how their proposed regions are evaluated. Our goal is to renegotiate the trade-off between the generality of these…

Computer Vision and Pattern Recognition · Computer Science 2021-06-01 Azim Ahmadzadeh , Dustin J. Kempton , Yang Chen , Rafal A. Angryk

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

In this paper, we propose a method for ensembling the outputs of multiple object detectors for improving detection performance and precision of bounding boxes on image data. We further extend it to video data by proposing a two-stage…

Computer Vision and Pattern Recognition · Computer Science 2021-02-10 Kateryna Chumachenko , Jenni Raitoharju , Alexandros Iosifidis , Moncef Gabbouj

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

We study utilizing auxiliary information in training data to improve the trustworthiness of machine learning models. Specifically, in the context of image classification, we propose to optimize a training objective that incorporates…

Computer Vision and Pattern Recognition · Computer Science 2021-08-24 Dharma KC , Chicheng Zhang

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

Improving object detectors against occlusion, blur and noise is a critical step to deploy detectors in real applications. Since it is not possible to exhaust all image defects through data collection, many researchers seek to generate hard…

Computer Vision and Pattern Recognition · Computer Science 2019-04-01 Zeyi Huang , Wei Ke , Dong Huang

While formal robustness verification has seen significant success in image classification, scaling these guarantees to object detection remains notoriously difficult due to complex non-linear coordinate transformations and…

Machine Learning · Computer Science 2026-03-06 Benedikt Brückner , Alejandro J. Mercado , Yanghao Zhang , Panagiotis Kouvaros , Alessio Lomuscio

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)…

Computer Vision and Pattern Recognition · Computer Science 2020-04-13 Jiale Li , Shujie Luo , Ziqi Zhu , Hang Dai , Andrey S. Krylov , Yong Ding , Ling Shao

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

Rotated bounding boxes drastically reduce output ambiguity of elongated objects, making it superior to axis-aligned bounding boxes. Despite the effectiveness, rotated detectors are not widely employed. Annotating rotated bounding boxes is…

Computer Vision and Pattern Recognition · Computer Science 2023-05-05 Tianyu Zhu , Bryce Ferenczi , Pulak Purkait , Tom Drummond , Hamid Rezatofighi , Anton van den Hengel

Long-tailed object detection faces great challenges because of its extremely imbalanced class distribution. Recent methods mainly focus on the classification bias and its loss function design, while ignoring the subtle influence of the…

Computer Vision and Pattern Recognition · Computer Science 2024-02-01 Ke Zhu , Minghao Fu , Jie Shao , Tianyu Liu , Jianxin Wu

Recently Deep Learning based Siamese Networks with region proposals for visual object tracking becoming more popular. These networks, while testing, perform extra computations on output if trained network, to predict the bounding box. This…

Image and Video Processing · Electrical Eng. & Systems 2020-01-28 Mohana Murali Dasari , Rama Krishna Sai Subrahmanyam Gorthi

Object detection and classification in 3D is a key task in Automated Driving (AD). LiDAR sensors are employed to provide the 3D point cloud reconstruction of the surrounding environment, while the task of 3D object bounding box detection in…

Computer Vision and Pattern Recognition · Computer Science 2018-08-08 Waleed Ali , Sherif Abdelkarim , Mohamed Zahran , Mahmoud Zidan , Ahmad El Sallab
‹ Prev 1 3 4 5 6 7 10 Next ›