1 code implementation • 19 Oct 2023 • Hanbo Bi, Yingchao Feng, Zhiyuan Yan, Yongqiang Mao, Wenhui Diao, Hongqi Wang, Xian Sun
In addition, to prevent the co-existence of multiple classes in remote sensing scenes from exacerbating the collapse of FSS generalization, we also propose a new Known-class Meta Suppressor (KMS) module to suppress the activation of known-class objects in the sample.
no code implementations • 24 Apr 2023 • Xuexue Li, Wenhui Diao, Yongqiang Mao, Peng Gao, Xiuhua Mao, Xinming Li, Xian Sun
One interaction for the guide is between two task decoders to address the feature confusion problem, and an occlusion decoupling head (ODH) is proposed to replace the general detection head.
no code implementations • 22 Mar 2023 • Jiahao Bao, Kaiqiang Chen, Xian Sun, Liangjin Zhao, Wenhui Diao, Menglong Yan
The majority of siamese network based trackers now in use treat each channel in the feature maps generated by the backbone network equally, making the similarity response map sensitive to background influence and hence challenging to focus on the target region.
no code implementations • 11 Jan 2023 • Yongqiang Mao, Kaiqiang Chen, Liangjin Zhao, Wei Chen, Deke Tang, Wenjie Liu, Zhirui Wang, Wenhui Diao, Xian Sun, Kun fu
Our Building3D is rooted in the SFFDE network for building elevation prediction, synchronized with a building extraction network for building masks, and then sequentially performs point cloud reconstruction, surface reconstruction (or CityGML model reconstruction).
no code implementations • ICCV 2023 • Yiran Yang, Dongshuo Yin, Xuee Rong, Xian Sun, Wenhui Diao, Xinming Li
Moreover, we construct a depth-guided matrix by the predicted depth gap of teacher and student to facilitate the model to learn more knowledge of farther objects in prediction level distillation.
no code implementations • 27 Nov 2022 • Xiaonan Lu, Wenhui Diao, Yongqiang Mao, Junxi Li, Peijin Wang, Xian Sun, Kun fu
Few-shot object detection, expecting detectors to detect novel classes with a few instances, has made conspicuous progress.
1 code implementation • 21 Jul 2022 • Yongqiang Mao, Kaiqiang Chen, Wenhui Diao, Xian Sun, Xiaonan Lu, Kun fu, Martin Weinmann
With receptive field fusion-and-stratification, RFFS-Net is more adaptable to the classification of regions with complex structures and extreme scale variations in large-scale ALS point clouds.
no code implementations • 11 Apr 2022 • Yongqiang Mao, Xian Sun, Kaiqiang Chen, Wenhui Diao, Zonghao Guo, Xiaonan Lu, Kun fu
Due to the unicity of receptive field, semantic segmentation of point clouds remains challenging for the expression of multi-receptive field features, which brings about the misclassification of instances with similar spatial structures.
no code implementations • 19 Jul 2021 • Yingchao Feng, Xian Sun, Wenhui Diao, Jihao Li, Xin Gao
In this paper, motivated by the residual learning and global aggregation, we propose a simple yet general and effective knowledge distillation framework called double similarity distillation (DSD) to improve the classification accuracy of all existing compact networks by capturing the similarity knowledge in pixel and category dimensions, respectively.
no code implementations • 9 Mar 2021 • Xian Sun, Peijin Wang, Zhiyuan Yan, Feng Xu, Ruiping Wang, Wenhui Diao, Jin Chen, Jihao Li, Yingchao Feng, Tao Xu, Martin Weinmann, Stefan Hinz, Cheng Wang, Kun fu
In this paper, we propose a novel benchmark dataset with more than 1 million instances and more than 15, 000 images for Fine-grAined object recognItion in high-Resolution remote sensing imagery which is named as FAIR1M.
no code implementations • Remote Sensing 2021 • Jiangqiao Yan, Liangjin Zhao, Wenhui Diao, Hongqi Wang, Xian Sun
With the objects to be detected becoming more complex, the problem of multi-scale object detection has attracted more and more attention, especially in the field of remote sensing detection.
Ranked #14 on Oriented Object Detection on DOTA 1.0
no code implementations • 9 Jan 2020 • Ruigang Niu, Xian Sun, Yu Tian, Wenhui Diao, Kaiqiang Chen, Kun fu
Semantic segmentation in very high resolution (VHR) aerial images is one of the most challenging tasks in remote sensing image understanding.
no code implementations • 22 Apr 2019 • Yingchao Feng, Wenhui Diao, Zhonghan Chang, Menglong Yan, Xian Sun, Xin Gao
The performance of object instance segmentation in remote sensing images has been greatly improved through the introduction of many landmark frameworks based on convolutional neural network.