no code implementations • 28 May 2024 • Shanshan Wang, Hao Zhou, Xun Yang, Zhenwei He, Mengzhu Wang, Xingyi Zhang, Meng Wang
Recent advancements in UDA models have demonstrated significant generalization capabilities on the target domain.
no code implementations • 1 Mar 2024 • Zhenwei He, Lei Zhang
\keywords{Object detection, incremental learning, causal feature.
no code implementations • International Journal of Computer Vision 2022 • Zhenwei He, Lei Zhang, Xinbo Gao, David Zhang
Our proposed MAF has two distinct contributions: (1) The Hierarchical Domain Feature Alignment (HDFA) module is introduced to minimize the image-level domain disparity, where Scale Reduction Module (SRM) reduces the feature map size without information loss and increases the training efficiency.
no code implementations • 3 Sep 2020 • Lei Zhang, Zhenwei He, Yi Yang, Liang Wang, Xinbo Gao
The traditional object retrieval task aims to learn a discriminative feature representation with intra-similarity and inter-dissimilarity, which supposes that the objects in an image are manually or automatically pre-cropped exactly.
no code implementations • ECCV 2020 • Zhenwei He, Lei Zhang
Unsupervised domain adaptive object detection is proposed recently to reduce the disparity between domains, where the source domain is label-rich while the target domain is label-agnostic.
1 code implementation • ICCV 2019 • Zhenwei He, Lei Zhang
Conventional object detection methods essentially suppose that the training and testing data are collected from a restricted target domain with expensive labeling cost.
no code implementations • 2 Apr 2018 • Zhenwei He, Lei Zhang, Wei Jia
This paper proposes a pedestrian detection and re-identification (re-id) integration net (I-Net) in an end-to-end learning framework.