1 code implementation • 18 Dec 2023 • Yuming Qiu, Aleksandra Pizurica, Qi Ming, Nicolas Nadisic
In addition, we especially built a dataset named SML2023 containing hundreds of scatter images with different markers and various levels of overlapping severity, and tested the proposed method and compared it to existing methods.
1 code implementation • CVPR 2023 • Qi Ming, Lingjuan Miao, Zhe Ma, Lin Zhao, Zhiqiang Zhou, Xuhui Huang, Yuanpei Chen, Yufei Guo
In this paper, we propose a Gradient-Corrected IoU (GCIoU) loss to achieve fast and accurate 3D bounding box regression.
no code implementations • 13 Oct 2021 • Qi Ming, Junjie Song, Zhiqiang Zhou
In this technical report, we analyzed the key issues of fine-grained object recognition, and use an oriented feature alignment network (OFA-Net) to achieve high-performance fine-grained oriented object recognition in optical remote sensing images.
no code implementations • 4 Jul 2021 • Hongwei Zhang, Weidong Zou, Hongbo Zhao, Qi Ming, Tijin Yan, Yuanqing Xia, Weipeng Cao
Inspired by this, we propose AdaL, with a transformation on the original gradient.
2 code implementations • NeurIPS 2021 • Xue Yang, Xiaojiang Yang, Jirui Yang, Qi Ming, Wentao Wang, Qi Tian, Junchi Yan
Taking the perspective that horizontal detection is a special case for rotated object detection, in this paper, we are motivated to change the design of rotation regression loss from induction paradigm to deduction methodology, in terms of the relation between rotation and horizontal detection.
Ranked #14 on Object Detection In Aerial Images on DOTA (using extra training data)
1 code implementation • 22 Mar 2021 • Qi Ming, Lingjuan Miao, Zhiqiang Zhou, Xue Yang, Yunpeng Dong
In this paper, we propose a Representation Invariance Loss (RIL) to optimize the bounding box regression for the rotating objects.
Ranked #27 on Object Detection In Aerial Images on DOTA (using extra training data)
2 code implementations • 28 Jan 2021 • Xue Yang, Junchi Yan, Qi Ming, Wentao Wang, Xiaopeng Zhang, Qi Tian
Boundary discontinuity and its inconsistency to the final detection metric have been the bottleneck for rotating detection regression loss design.
Ranked #16 on Object Detection In Aerial Images on DOTA (using extra training data)
1 code implementation • 18 Jan 2021 • Qi Ming, Lingjuan Miao, Zhiqiang Zhou, Yunpeng Dong
The proposed framework creates more powerful semantic representations for objects in remote sensing images and achieves high-performance real-time object detection.
Ranked #44 on Object Detection In Aerial Images on DOTA (using extra training data)
2 code implementations • 8 Dec 2020 • Qi Ming, Zhiqiang Zhou, Lingjuan Miao, Hongwei Zhang, Linhao Li
With the newly introduced DAL, we achieve superior detection performance for arbitrary-oriented objects with only a few horizontal preset anchors.
Ranked #1 on Multi-Oriented Scene Text Detection on ICDAR2015 (using extra training data)