1 code implementation • 28 Nov 2023 • Kunpeng Wang, Chenglong Li, Zhengzheng Tu, Zhengyi Liu, Bin Luo
Existing single-modal and multi-modal salient object detection (SOD) methods focus on designing specific architectures tailored for their respective tasks.
no code implementations • 6 Aug 2023 • Linbo Wang, Jing Wu, Xianyong Fang, Zhengyi Liu, Chenjie Cao, Yanwei Fu
First, we propose a Local Feature Consensus (LFC) plugin block to augment the features of existing models.
1 code implementation • 17 Mar 2023 • Zhengyi Liu, Xiaoshen Huang, Guanghui Zhang, Xianyong Fang, Linbo Wang, Bin Tang
To further polish the expanded labels, we propose a prediction module to alleviate the sharpness of boundary.
1 code implementation • 8 Jan 2023 • Bin Tang, Zhengyi Liu, Yacheng Tan, Qian He
To solve the second problem, a dual-direction short connection fusion module is used to optimize the output features of HRFormer, thereby enhancing the detailed representation of objects at the output level.
1 code implementation • 8 Jan 2023 • Zhengyi Liu, Wei Wu, Yacheng Tan, Guanghui Zhang
To better excavate multi-modal information, we use count-guided multi-modal fusion and modal-guided count enhancement to achieve the impressive performance.
1 code implementation • 21 May 2022 • Zhengyi Liu, Zhili Zhang, Wei Wu
The foreground is just object, while foreground minus background is considered as boundary.
1 code implementation • 12 Apr 2022 • Zhengyi Liu, Yacheng Tan, Qian He, Yun Xiao
It is driven by Swin Transformer to extract the hierarchical features, boosted by attention mechanism to bridge the gap between two modalities, and guided by edge information to sharp the contour of salient object.
1 code implementation • 9 Aug 2021 • Zhengyi Liu, YuAn Wang, Zhengzheng Tu, Yun Xiao, Bin Tang
In view of the more contribution of high-level features for the performance, we propose a triplet transformer embedding module to enhance them by learning long-range dependencies across layers.