no code implementations • 28 Apr 2021 • Xin Yi, Jiahao Wu, Bo Ma, Yangtong Ou, Longyao Liu
Object detection is widely studied in computer vision filed.
no code implementations • 19 Apr 2021 • Yulin Zhang, Bo Ma, Longyao Liu, Xin Yi
The one-shot Person Re-ID scenario faces two kinds of uncertainties when constructing the prediction model from $X$ to $Y$.
no code implementations • 6 Feb 2021 • Xin Yi, Bo Ma, Yulin Zhang, Longyao Liu, Jiahao Wu
To alleviate the intra-domain gap of the synthetic domain, we propose an intra-domain adaptation to align distributions of other subsets to the optimal subset by adversarial learning.
no code implementations • 30 Nov 2020 • Longyao Liu, Bo Ma, Yulin Zhang, Xin Yi, Haozhi Li
In this paper, we carefully analyze the characteristics of FSOD, and present that a general few-shot detector should consider the explicit decomposition of two subtasks, as well as leveraging information from both of them to enhance feature representations.