1 code implementation • ICCV 2023 • Shaoyu Zhang, Chen Chen, Silong Peng
Specifically, complementary to the object-level classification loss for model discrimination, we design a generalized average precision (GAP) loss to explicitly optimize the global-level score ranking across different objects.
no code implementations • CVPR 2023 • YuAn Wang, Kun Yu, Chen Chen, Xiyuan Hu, Silong Peng
To address this issue, we propose a Spatial-Frequency Dynamic Graph method to exploit the relation-aware features in spatial and frequency domains via dynamic graph learning.
no code implementations • 11 Oct 2021 • Shaoyu Zhang, Chen Chen, Xiujuan Zhang, Silong Peng
When applying mixup to long-tailed data, a label suppression issue arises, where the frequency of label occurrence for each class is imbalanced and most of the new examples will be completely or partially assigned with head labels.
1 code implementation • 24 Sep 2021 • Wen Qian, Xue Yang, Silong Peng, Junchi Yan, Xiujuan Zhang
We classify the discontinuity of loss in both five-param and eight-param rotated object detection methods as rotation sensitivity error (RSE) which will result in performance degeneration.
1 code implementation • 23 Sep 2021 • Zhenfeng Fan, Silong Peng, Shihong Xia
This method is then extended to 3D surface by formulating a local registration problem for dividing and a linear least-square problem for diffusing, with constraints on fixed features.
1 code implementation • 21 Apr 2021 • Shaoyu Zhang, Chen Chen, Xiyuan Hu, Silong Peng
Existing methods usually modify the classification loss to increase the learning focus on tail classes, which unexpectedly sacrifice the performance on head classes.
1 code implementation • 7 Sep 2020 • Min Cao, Chen Chen, Hao Dou, Xiyuan Hu, Silong Peng, Arjan Kuijper
Most existing person re-identification methods compute pairwise similarity by extracting robust visual features and learning the discriminative metric.
no code implementations • 1 May 2020 • Hao Dou, Chen Chen, Xiyuan Hu, Zuxing Xuan, Zhisen Hu, Silong Peng
Generative Adversarial Networks (GAN) have been employed for face super resolution but they bring distorted facial details easily and still have weakness on recovering realistic texture.
no code implementations • 9 Apr 2020 • Zhe Shen, Peng Sun, Yubo Lang, Lei Liu, Silong Peng
Therefore we present a novel optic-physical method to discriminate splicing edges from natural edges in a tampered image.
2 code implementations • 19 Nov 2019 • Wen Qian, Xue Yang, Silong Peng, Yue Guo, Junchi Yan
Popular rotated detection methods usually use five parameters (coordinates of the central point, width, height, and rotation angle) to describe the rotated bounding box and l1-loss as the loss function.
Ranked #43 on Object Detection In Aerial Images on DOTA (using extra training data)
no code implementations • ECCV 2018 • Zhenfeng Fan, Xiyuan Hu, Chen Chen, Silong Peng
The dense correspondence goal is revisited in two perspectives: semantic and topological correspondence.
no code implementations • 25 May 2018 • Chen Chen, Min Cao, Xiyuan Hu, Silong Peng
Ideally person re-identification seeks for perfect feature representation and metric model that re-identify all various pedestrians well in non-overlapping views at different locations with different camera configurations, which is very challenging.