2 code implementations • 23 Oct 2023 • Xinyu Huang, Yi-Jie Huang, Youcai Zhang, Weiwei Tian, Rui Feng, Yuejie Zhang, Yanchun Xie, Yaqian Li, Lei Zhang
Specifically, for predefined commonly used tag categories, RAM++ showcases 10. 2 mAP and 15. 4 mAP enhancements over CLIP on OpenImages and ImageNet.
2 code implementations • 6 Jun 2023 • Youcai Zhang, Xinyu Huang, Jinyu Ma, Zhaoyang Li, Zhaochuan Luo, Yanchun Xie, Yuzhuo Qin, Tong Luo, Yaqian Li, Shilong Liu, Yandong Guo, Lei Zhang
We are releasing the RAM at \url{https://recognize-anything. github. io/} to foster the advancements of large models in computer vision.
1 code implementation • 15 Mar 2023 • Youcai Zhang, Yuzhuo Qin, Hengwei Liu, Yanhao Zhang, Yaqian Li, Xiaodong Gu
Knowledge distillation (KD) has been extensively studied in single-label image classification.
2 code implementations • 10 Mar 2023 • Xinyu Huang, Youcai Zhang, Jinyu Ma, Weiwei Tian, Rui Feng, Yuejie Zhang, Yaqian Li, Yandong Guo, Lei Zhang
This paper presents Tag2Text, a vision language pre-training (VLP) framework, which introduces image tagging into vision-language models to guide the learning of visual-linguistic features.
1 code implementation • 12 Jul 2022 • Xinyu Huang, Youcai Zhang, Ying Cheng, Weiwei Tian, RuiWei Zhao, Rui Feng, Yuejie Zhang, Yaqian Li, Yandong Guo, Xiaobo Zhang
However, the image-text pairs co-occurrent on the Internet typically lack explicit alignment information, which is suboptimal for VLP.
2 code implementations • 13 Dec 2021 • Youcai Zhang, Yuhao Cheng, Xinyu Huang, Fei Wen, Rui Feng, Yaqian Li, Yandong Guo
Multi-label learning in the presence of missing labels (MLML) is a challenging problem.
no code implementations • 29 Sep 2021 • Haizhou Shi, Youcai Zhang, Zijin Shen, Siliang Tang, Yaqian Li, Yandong Guo, Yueting Zhuang
This paper investigates the feasibility of federated representation learning under the constraints of communication cost and privacy protection.
no code implementations • 30 Jul 2021 • Haizhou Shi, Youcai Zhang, Siliang Tang, Wenjie Zhu, Yaqian Li, Yandong Guo, Yueting Zhuang
It is a consensus that small models perform quite poorly under the paradigm of self-supervised contrastive learning.
1 code implementation • ECCV 2020 • Youcai Zhang, Zhonghao Lan, Yuchen Dai, Fangao Zeng, Yan Bai, Jie Chang, Yichen Wei
With ten teacher-student combinations on six datasets, PAD promotes the performance of existing distillation methods and outperforms recent state-of-the-art methods.
2 code implementations • 11 Mar 2020 • Yangyao Chen, H. J. Mo, Cheng Li, Huiyuan Wang, Xiaohu Yang, Youcai Zhang, Kai Wang
Using decision trees built with the random ensemble method, we find that the correlation between halo concentration and assembly history is tight: more than 60% of the variance in halo concentration can be explained by assembly history alone.
Astrophysics of Galaxies Cosmology and Nongalactic Astrophysics