4 code implementations • CVPR 2021 • Ye Zheng, JiaHong Wu, Yongqiang Qin, Faen Zhang, Li Cui
We follow this motivation and propose a new task set named zero-shot instance segmentation (ZSI).
no code implementations • 1 Jan 2021 • Liang Song, Jinlu Liu, Yongqiang Qin
We first introduce and derive a theoretical upper bound of error rate which is constrained to 1) linear separability in the learned embedding space and 2) discrepancy of task-specific and task-independent classifier.
no code implementations • 23 Nov 2020 • Jinlu Liu, Liang Song, Yongqiang Qin
On each task, the inner loop aims to learn optimized prototypes from the query images.
no code implementations • 10 Feb 2020 • Jinlu Liu, Yongqiang Qin
Furthermore, to extract representative prototypes of the new classes, we use adaptation and fusion for prototype refinement.
no code implementations • 25 Nov 2019 • Liang Song, Jinlu Liu, Yongqiang Qin
Many Few-Shot Learning research works have two stages: pre-training base model and adapting to novel model.
1 code implementation • ECCV 2020 • Jinlu Liu, Liang Song, Yongqiang Qin
Few-shot learning requires to recognize novel classes with scarce labeled data.
no code implementations • 5 May 2019 • Faen Zhang, Xinyu Fan, Guo Ai, Jianfei Song, Yongqiang Qin, Jia-Hong Wu
Face detection has witnessed significant progress due to the advances of deep convolutional neural networks (CNNs).
Ranked #5 on Face Detection on WIDER Face (Hard)