1 code implementation • 3 Jul 2023 • Changhong Fu, Liangliang Yao, Haobo Zuo, Guangze Zheng, Jia Pan
However, the state-of-the-art (SOTA) DA still lacks the potential object with accurate pixel-level location and boundary to generate the high-quality target domain training sample.
1 code implementation • 8 Mar 2023 • Liangliang Yao, Changhong Fu, Sihang Li, Guangze Zheng, Junjie Ye
The proposed method designs a new task-specific object saliency mining network to refine the cross-correlation operation and effectively discriminate foreground and background information.