1 code implementation • 30 Mar 2024 • Sanghyun Jo, Fei Pan, In-Jae Yu, KyungSu Kim
Weakly-supervised semantic segmentation (WSS) ensures high-quality segmentation with limited data and excels when employed as input seed masks for large-scale vision models such as Segment Anything.
1 code implementation • 27 Mar 2024 • Chenshuang Zhang, Fei Pan, Junmo Kim, In So Kweon, Chengzhi Mao
In this work, we introduce generative model as a data source for synthesizing hard images that benchmark deep models' robustness.
no code implementations • 19 Dec 2023 • Fei Pan, Sangryul Jeon, Brian Wang, Frank Mckenna, Stella X. Yu
The proposed workflow contains two key components: image-level captioning and segment-level captioning for the building images based on the vocabularies pertinent to structural and civil engineering.
no code implementations • 21 Sep 2023 • Fei Pan, Xu Yin, Seokju Lee, Axi Niu, SungEui Yoon, In So Kweon
Then, we propose a semantic mining module that takes the object masks to refine the pseudo labels in the target domain.
no code implementations • 27 Jan 2023 • Fei Pan, Yutong Wu, Kangning Cui, Shuxun Chen, Yanfang Li, Yaofang Liu, Adnan Shakoor, Han Zhao, Beijia Lu, Shaohua Zhi, Raymond Chan, Dong Sun
In this study, we developed a novel deep-learning algorithm called dual-view selective instance segmentation network (DVSISN) for segmenting unstained adherent cells in differential interference contrast (DIC) images.
no code implementations • 19 Jul 2022 • Fei Pan, Sungsu Hur, Seokju Lee, Junsik Kim, In So Kweon
Open compound domain adaptation (OCDA) considers the target domain as the compound of multiple unknown homogeneous subdomains.
no code implementations • 1 Jun 2022 • Fei Pan, Francois Rameau, Junsik Kim, In So Kweon
In this work, we propose a new domain adaptation framework for semantic segmentation with annotated points via active selection.
no code implementations • ICCV 2021 • Seokju Lee, Francois Rameau, Fei Pan, In So Kweon
Experiments on KITTI, Cityscapes, and Waymo Open Dataset demonstrate the relevance of our approach and show that our method outperforms state-of-the-art algorithms for the tasks of self-supervised monocular depth estimation, object motion segmentation, monocular scene flow estimation, and visual odometry.
no code implementations • 26 Jul 2021 • Fei Pan, Chunlei Xu, Jie Guo, Yanwen Guo
In order to obtain the similarity of a pair of videos, we predict the alignment scores between all pairs of temporal positions in the two videos with the temporal alignment prediction function.
no code implementations • 26 Jul 2021 • Fei Pan, Chunlei Xu, Jie Guo, Yanwen Guo
We introduce a transductive maximum margin classifier for few-shot learning (FS-TMMC).
no code implementations • 27 May 2021 • Jinhui Yuan, Fei Pan, Chunting Zhou, Tao Qin, Tie-Yan Liu
We further establish connections between this principle and the theory of Bayesian optimal classification, and empirically verify that larger entropy of the outputs of a deep neural network indeed corresponds to a better classification accuracy.
no code implementations • 25 May 2021 • Liyi Guo, Junqi Jin, Haoqi Zhang, Zhenzhe Zheng, Zhiye Yang, Zhizhuang Xing, Fei Pan, Lvyin Niu, Fan Wu, Haiyang Xu, Chuan Yu, Yuning Jiang, Xiaoqiang Zhu
To achieve this goal, the advertising platform needs to identify the advertiser's optimization objectives, and then recommend the corresponding strategies to fulfill the objectives.
no code implementations • ECCV 2020 • Inkyu Shin, Sanghyun Woo, Fei Pan, Inso Kweon
However, since only the confident predictions are taken as pseudo labels, existing self-training approaches inevitably produce sparse pseudo labels in practice.
2 code implementations • 24 Jun 2020 • Yang Zhang, Moyun Liu, Jingwu He, Fei Pan, Yanwen Guo
The proposed framework combines adjacency-graphs and kernel spectral clustering based graphs (KSC-graphs) according to a new definition named affinity nodes of multi-scale superpixels.
1 code implementation • CVPR 2020 • Fei Pan, Inkyu Shin, Francois Rameau, Seokju Lee, In So Kweon
Finally, to decrease the intra-domain gap, we propose to employ a self-supervised adaptation technique from the easy to the hard split.
Ranked #2 on Domain Adaptation on Synscapes-to-Cityscapes
no code implementations • 19 Aug 2019 • Dagui Chen, Junqi Jin, Wei-Nan Zhang, Fei Pan, Lvyin Niu, Chuan Yu, Jun Wang, Han Li, Jian Xu, Kun Gai
We refer to this process as Leverage.
1 code implementation • CVPR 2019 • Junsik Kim, Tae-Hyun Oh, Seokju Lee, Fei Pan, In So Kweon
We take an approach to learn a generalizable embedding space for novel tasks.
no code implementations • 13 Nov 2018 • Fei Pan, Hans-Arno Jacobsen
In this paper, we present a new algorithm called PanJoin which has high throughput on large windows and supports both equi-join and non-equi-join.
Databases
no code implementations • 27 Feb 2017 • Han Zhu, Junqi Jin, Chang Tan, Fei Pan, Yifan Zeng, Han Li, Kun Gai
Moreover, the platform has to be responsible for the business revenue and user experience.