no code implementations • ICCV 2023 • Jiexi Yan, Zhihui Yin, Erkun Yang, Yanhua Yang, Heng Huang
Most existing DML methods focus on improving the model robustness against category shift to keep the performance on unseen categories.
no code implementations • CVPR 2022 • Jiexi Yan, Lei Luo, Chenghao Xu, Cheng Deng, Heng Huang
While in metric space, we utilize weakly-supervised contrastive learning to excavate these negative correlations hidden in noisy data.
no code implementations • 29 Oct 2021 • Jiexi Yan, Lei Luo, Cheng Deng, Heng Huang
Since these noisy labels often cause severe performance degradation, it is crucial to enhance the robustness and generalization ability of DML.
1 code implementation • 22 Jun 2021 • Zhipeng Wang, Hao Wang, Jiexi Yan, Aming Wu, Cheng Deng
Most existing methods regard ZS-SBIR as a traditional classification problem and employ a cross-entropy or triplet-based loss to achieve retrieval, which neglect the problems of the domain gap between sketches and natural images and the large intra-class diversity in sketches.
no code implementations • CVPR 2021 • Jiexi Yan, Lei Luo, Cheng Deng, Heng Huang
Learning feature embedding directly from images without any human supervision is a very challenging and essential task in the field of computer vision and machine learning.