1 code implementation • CVPR 2018 • Maoke Yang, Kun Yu, Chi Zhang, Zhiwei Li, Kuiyuan Yang
To this end, we propose Densely connected Atrous Spatial Pyramid Pooling (DenseASPP), which connects a set of atrous convolutional layers in a dense way, such that it generates multi-scale features that not only cover a larger scale range, but also cover that scale range densely, without significantly increasing the model size.
Ranked #5 on Semantic Segmentation on SkyScapes-Dense
2 code implementations • 9 Sep 2019 • Youmin Zhang, Yimin Chen, Xiao Bai, Suihanjin Yu, Kun Yu, Zhiwei Li, Kuiyuan Yang
However, disparity is just a byproduct of a matching process modeled by cost volume, while indirectly learning cost volume driven by disparity regression is prone to overfitting since the cost volume is under constrained.
1 code implementation • ECCV 2020 • Chang Shu, Kun Yu, Zhixiang Duan, Kuiyuan Yang
Photometric loss is widely used for self-supervised depth and egomotion estimation.
no code implementations • 15 Apr 2021 • Shuiqiao Yang, Sunny Verma, Borui Cai, Jiaojiao Jiang, Kun Yu, Fang Chen, Shui Yu
Recent works for attributed network clustering utilize graph convolution to obtain node embeddings and simultaneously perform clustering assignments on the embedding space.
no code implementations • 16 Feb 2022 • Yimu Wang, Kun Yu, Yan Wang, Hui Xue
In this paper, to extract a better feature for advancing the performance, we propose a novel method, namely multi-view fusion transformer (MVFT) along with a novel attention mechanism.
no code implementations • 27 Mar 2022 • Neng Wang, Yang Bai, Kun Yu, Yong Jiang, Shu-Tao Xia, Yan Wang
Face forgery has attracted increasing attention in recent applications of computer vision.
no code implementations • CVPR 2023 • YuAn Wang, Kun Yu, Chen Chen, Xiyuan Hu, Silong Peng
To address this issue, we propose a Spatial-Frequency Dynamic Graph method to exploit the relation-aware features in spatial and frequency domains via dynamic graph learning.