2 code implementations • 12 Apr 2024 • Zhiwei Yang, Yucong Meng, Kexue Fu, Shuo Wang, Zhijian Song
When activating class objects, we argue that the false activation stems from the bias to the ambiguous regions during the feature extraction.
Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation
1 code implementation • 28 Feb 2024 • Zhiwei Yang, Kexue Fu, Minghong Duan, Linhao Qu, Shuo Wang, Zhijian Song
In this work, we devise a 'Separate and Conquer' scheme SeCo to tackle this issue from dimensions of image space and feature space.
1 code implementation • ICCV 2023 • Mingzhi Yuan, Kexue Fu, Zhihao LI, Yucong Meng, Manning Wang
Point cloud registration is a task to estimate the rigid transformation between two unaligned scans, which plays an important role in many computer vision applications.
1 code implementation • NeurIPS 2023 • Linhao Qu, Xiaoyuan Luo, Kexue Fu, Manning Wang, Zhijian Song
Our approach incorporates the utilization of GPT-4 in a question-and-answer mode to obtain language prior knowledge at both the instance and bag levels, which are then integrated into the instance and bag level language prompts.
1 code implementation • 9 Nov 2022 • Kexue Fu, Jiazheng Luo, Xiaoyuan Luo, Shaolei Liu, Chenxi Zhang, Manning Wang
In this paper, we propose a novel deep graph matching-based framework for point cloud registration.
1 code implementation • 27 Jul 2022 • Kexue Fu, Mingzhi Yuan, Manning Wang
Masked language modeling (MLM) has become one of the most successful self-supervised pre-training task.
1 code implementation • 3 Apr 2022 • Kexue Fu, Peng Gao, Shaolei Liu, Renrui Zhang, Yu Qiao, Manning Wang
We propose to use the dynamically updated momentum encoder as the tokenizer, which is updated and outputs the dynamic supervision signal along with the training process.
no code implementations • 9 Feb 2022 • Kexue Fu, Peng Gao, Renrui Zhang, Hongsheng Li, Yu Qiao, Manning Wang
Especially, we develop a variant of ViT for 3D point cloud feature extraction, which also achieves comparable results with existing backbones when combined with our framework, and visualization of the attention maps show that our model does understand the point cloud by combining the global shape information and multiple local structural information, which is consistent with the inspiration of our representation learning method.
2 code implementations • 22 Dec 2021 • Liang Pan, Tong Wu, Zhongang Cai, Ziwei Liu, Xumin Yu, Yongming Rao, Jiwen Lu, Jie zhou, Mingye Xu, Xiaoyuan Luo, Kexue Fu, Peng Gao, Manning Wang, Yali Wang, Yu Qiao, Junsheng Zhou, Xin Wen, Peng Xiang, Yu-Shen Liu, Zhizhong Han, Yuanjie Yan, Junyi An, Lifa Zhu, Changwei Lin, Dongrui Liu, Xin Li, Francisco Gómez-Fernández, Qinlong Wang, Yang Yang
Based on the MVP dataset, this paper reports methods and results in the Multi-View Partial Point Cloud Challenge 2021 on Completion and Registration.
1 code implementation • 19 Nov 2021 • Renrui Zhang, Ziyao Zeng, Ziyu Guo, Xinben Gao, Kexue Fu, Jianbo Shi
We reverse the conventional design of applying convolution on voxels and attention to points.
Ranked #36 on 3D Part Segmentation on ShapeNet-Part
no code implementations • 12 Apr 2021 • Xiaoyuan Luo, Shaolei Liu, Kexue Fu, Manning Wang, Zhijian Song
In the UDA architecture, an encoder is shared between the networks for the self-supervised task and the main task of point cloud classification or segmentation, so that the encoder can be trained to extract features suitable for both the source and the target domain data.
2 code implementations • CVPR 2021 • Kexue Fu, Shaolei Liu, Xiaoyuan Luo, Manning Wang
In this paper, we propose a novel deep graph matchingbased framework for point cloud registration.