3 code implementations • 23 Nov 2022 • Xianzhe Xu, Yiqi Jiang, Weihua Chen, Yilun Huang, Yuan Zhang, Xiuyu Sun
Based on these new techs, we build a suite of models at various scales to meet the needs of different scenarios.
Ranked #40 on Real-Time Object Detection on MS COCO
2 code implementations • ICLR 2022 • Yiqi Jiang, Zhiyu Tan, Junyan Wang, Xiuyu Sun, Ming Lin, Hao Li
This heavy-backbone design paradigm is mostly due to the historical legacy when transferring image recognition models to object detection rather than an end-to-end optimized design for object detection.
no code implementations • 23 Aug 2021 • Yiqi Jiang, Weihua Chen, Xiuyu Sun, Xiaoyu Shi, Fan Wang, Hao Li
Recently, GAN based method has demonstrated strong effectiveness in generating augmentation data for person re-identification (ReID), on account of its ability to bridge the gap between domains and enrich the data variety in feature space.
1 code implementation • 20 May 2021 • Hao Luo, Weihua Chen, Xianzhe Xu, Jianyang Gu, Yuqi Zhang, Chong Liu, Yiqi Jiang, Shuting He, Fan Wang, Hao Li
We mainly focus on four points, i. e. training data, unsupervised domain-adaptive (UDA) training, post-processing, model ensembling in this challenge.
1 code implementation • 25 Dec 2020 • Jianyang Gu, Hao Luo, Weihua Chen, Yiqi Jiang, Yuqi Zhang, Shuting He, Fan Wang, Hao Li, Wei Jiang
Considering the large gap between the source domain and target domain, we focused on solving two biases that influenced the performance on domain adaptive pedestrian Re-ID and proposed a two-stage training procedure.