1 code implementation • CVPR 2022 • Xiang An, Jiankang Deng, Jia Guo, Ziyong Feng, Xuhan Zhu, Jing Yang, Tongliang Liu
In each iteration, positive class centers and a random subset of negative class centers are selected to compute the margin-based softmax loss.
1 code implementation • 12 Apr 2023 • Dong Wang, Jia Guo, Qiqi Shao, Haochi He, Zhian Chen, Chuanbao Xiao, Ajian Liu, Sergio Escalera, Hugo Jair Escalante, Zhen Lei, Jun Wan, Jiankang Deng
Leveraging the WFAS dataset and Protocol 1 (Known-Type), we host the Wild Face Anti-Spoofing Challenge at the CVPR2023 workshop.
98 code implementations • CVPR 2019 • Jiankang Deng, Jia Guo, Jing Yang, Niannan Xue, Irene Kotsia, Stefanos Zafeiriou
Recently, a popular line of research in face recognition is adopting margins in the well-established softmax loss function to maximize class separability.
Ranked #1 on Face Verification on Labeled Faces in the Wild (using extra training data)
3 code implementations • 5 Dec 2018 • Jia Guo, Jiankang Deng, Niannan Xue, Stefanos Zafeiriou
Face Analysis Project on MXNet
Ranked #1 on Face Alignment on IBUG
73 code implementations • 2 May 2019 • Jiankang Deng, Jia Guo, Yuxiang Zhou, Jinke Yu, Irene Kotsia, Stefanos Zafeiriou
Face Analysis Project on MXNet
Ranked #3 on Face Detection on WIDER Face (Medium)
2 code implementations • ECCV 2020 • Jiankang Deng, Jia Guo, Tongliang Liu, Mingming Gong, Stefanos Zafeiriou
In this paper, we relax the intra-class constraint of ArcFace to improve the robustness to label noise.
5 code implementations • ICLR 2022 • Jia Guo, Jiankang Deng, Alexandros Lattas, Stefanos Zafeiriou
Although tremendous strides have been made in uncontrolled face detection, efficient face detection with a low computation cost as well as high precision remains an open challenge.
Ranked #8 on Face Detection on WIDER Face (Medium)
1 code implementation • 18 Aug 2021 • Jiankang Deng, Jia Guo, Xiang An, Zheng Zhu, Stefanos Zafeiriou
In this workshop, we organize Masked Face Recognition (MFR) challenge and focus on bench-marking deep face recognition methods under the existence of facial masks.
4 code implementations • 28 Mar 2022 • Xiang An, Jiankang Deng, Jia Guo, Ziyong Feng, Xuhan Zhu, Jing Yang, Tongliang Liu
In each iteration, positive class centers and a random subset of negative class centers are selected to compute the margin-based softmax loss.
Ranked #1 on Face Recognition on MFR
4 code implementations • 15 Aug 2022 • Jia Guo, Jinke Yu, Alexandros Lattas, Jiankang Deng
Even though 3D face reconstruction has achieved impressive progress, most orthogonal projection-based face reconstruction methods can not achieve accurate and consistent reconstruction results when the face is very close to the camera due to the distortion under the perspective projection.
4 code implementations • 6 Dec 2022 • Evangelos Ververas, Polydefkis Gkagkos, Jiankang Deng, Michail Christos Doukas, Jia Guo, Stefanos Zafeiriou
To close the gap between image domains, we create a large-scale dataset of diverse faces with gaze pseudo-annotations, which we extract based on the 3D geometry of the scene, and design a multi-view supervision framework to balance their effect during training.
2 code implementations • 12 Apr 2023 • Xiang An, Jiankang Deng, Kaicheng Yang, Jaiwei Li, Ziyong Feng, Jia Guo, Jing Yang, Tongliang Liu
To further enhance the low-dimensional feature representation, we randomly select partial feature dimensions when calculating the similarities between embeddings and class-wise prototypes.
Ranked #1 on Image Retrieval on SOP (using extra training data)
1 code implementation • ICCV 2023 • Kaicheng Yang, Jiankang Deng, Xiang An, Jiawei Li, Ziyong Feng, Jia Guo, Jing Yang, Tongliang Liu
However, the presence of intrinsic noise and unmatched image-text pairs in web data can potentially affect the performance of representation learning.
1 code implementation • 4 Apr 2024 • Longxu Dou, Qian Liu, Guangtao Zeng, Jia Guo, Jiahui Zhou, Wei Lu, Min Lin
We present Sailor, a family of open language models ranging from 0. 5B to 7B parameters, tailored for South-East Asian (SEA) languages.
1 code implementation • 16 Dec 2022 • Jee Seok Yoon, Chenghao Zhang, Heung-Il Suk, Jia Guo, Xiaoxiao Li
To this end, we propose a sequence-aware diffusion model (SADM) for the generation of longitudinal medical images.
1 code implementation • 15 Jan 2020 • Nanyan Zhu, Chen Liu, Zakary S. Singer, Tal Danino, Andrew F. Laine, Jia Guo
The ability to extrapolate gene expression dynamics in living single cells requires robust cell segmentation, and one of the challenges is the amorphous or irregularly shaped cell boundaries.
1 code implementation • 15 Oct 2020 • Jia Guo, Minghao Chen, Yao Hu, Chen Zhu, Xiaofei He, Deng Cai
We investigate this problem by study the gap of confidence between teacher and student.
1 code implementation • 14 Jun 2021 • Xinzi He, Jia Guo, Xuzhe Zhang, Hanwen Bi, Sarah Gerard, David Kaczka, Amin Motahari, Eric Hoffman, Joseph Reinhardt, R. Graham Barr, Elsa Angelini, Andrew Laine
We introduce a recursive refinement network (RRN) for unsupervised medical image registration, to extract multi-scale features, construct normalized local cost correlation volume and recursively refine volumetric deformation vector fields.
Ranked #1 on Image Registration on DIR-LAB COPDgene
1 code implementation • 21 Jan 2022 • Vishwanatha M. Rao, Zihan Wan, Soroush Arabshahi, David J. Ma, Pin-Yu Lee, Ye Tian, Xuzhe Zhang, Andrew F. Laine, Jia Guo
Transformers have demonstrated success in natural image segmentation and have recently been applied to 3D medical image segmentation tasks due to their ability to capture long-distance relationships in the input where the local receptive fields of CNNs struggle.
1 code implementation • 28 May 2021 • Xuzhe Zhang, Xinzi He, Jia Guo, Nabil Ettehadi, Natalie Aw, David Semanek, Jonathan Posner, Andrew Laine, Yun Wang
Magnetic resonance imaging (MRI) noninvasively provides critical information about how human brain structures develop across stages of life.
Generative Adversarial Network Vocal Bursts Intensity Prediction
1 code implementation • EMNLP 2021 • Jia Guo, Stanley Kok
In contrast, hyperbolic models are effective at modeling hierarchical relations, but do not perform as well on patterns on which circular rotation excels.
1 code implementation • 16 Mar 2023 • Xuzhe Zhang, Yuhao Wu, Elsa Angelini, Ang Li, Jia Guo, Jerod M. Rasmussen, Thomas G. O'Connor, Pathik D. Wadhwa, Andrea Parolin Jackowski, Hai Li, Jonathan Posner, Andrew F. Laine, Yun Wang
In this study, we introduce Masked Autoencoding and Pseudo-Labeling Segmentation (MAPSeg), a $\textbf{unified}$ UDA framework with great versatility and superior performance for heterogeneous and volumetric medical image segmentation.
1 code implementation • 11 Jun 2019 • Jia Guo, Miodrag Potkonjak
The commercialization of deep learning creates a compelling need for intellectual property (IP) protection.
1 code implementation • 22 Dec 2022 • ShengJie Liu, Jia Guo, Chenyang Yang
Based on the observation that the mismatched permutation property from the policies and the information loss during the update of hidden representations have large impact on the learning performance and efficiency, in this paper we propose a unified framework to learn permutable wireless policies with multidimensional GNNs.
1 code implementation • 31 May 2023 • Jia Guo, Liying Cheng, Wenxuan Zhang, Stanley Kok, Xin Li, Lidong Bing
In this work, we for the first time propose a challenging argument quadruplet extraction task (AQE), which can provide an all-in-one extraction of four argumentative components, i. e., claims, evidence, evidence types, and stances.
1 code implementation • 3 Apr 2023 • Jia Guo, Stanley Kok, Lidong Bing
In addition, we introduce two new data regimes to mimic more realistic scenarios with annotation errors and evaluate our sampling strategy.
no code implementations • 1 Aug 2018 • Sheng Chen, Jia Guo, Yang Liu, Xiang Gao, Zhen Han
In this paper, we propose a novel Global Norm-Aware Pooling (GNAP) block, which reweights local features in a convolutional neural network (CNN) adaptively according to their L2 norms and outputs a global feature vector with a global average pooling layer.
no code implementations • 30 Oct 2019 • Jia Guo, Chenyang Yang
Deep neural networks (DNNs) have been employed for designing wireless networks in many aspects, such as transceiver optimization, resource allocation, and information prediction.
no code implementations • 10 Dec 2019 • Jia Guo, Yuxuan Mu, Dong Xue, Huiqi Li, Junxian Chen, Huanxin Yan, Hailin Xu, Wei Wang
This study aims to develop an analysis system that can automatically locate four anatomic landmarks, measure BA and CAG for fracture assessment, identify fractured calcaneus, and segment fractured regions.
no code implementations • 15 Jan 2020 • Haoran Sun, Xueqing Liu, Xinyang Feng, Chen Liu, Nanyan Zhu, Sabrina J. Gjerswold-Selleck, Hong-Jian Wei, Pavan S. Upadhyayula, Angeliki Mela, Cheng-Chia Wu, Peter D. Canoll, Andrew F. Laine, J. Thomas Vaughan, Scott A. Small, Jia Guo
Together, these studies validate our hypothesis that a deep learning approach can potentially replace the need for GBCAs in brain MRI.
no code implementations • 29 Jan 2020 • Jia Guo, Chenyang Yang
In this paper, we show that two kinds of permutation invariant properties widely existed in wireless tasks can be harnessed to reduce the number of model parameters and hence the sample and computational complexity for training.
no code implementations • 22 Jul 2020 • Sang Won Lee, Yueh-Ting Chiu, Philip Brudnicki, Audrey M. Bischoff, Angus Jelinek, Jenny Zijun Wang, Danielle R. Bogdanowicz, Andrew F. Laine, Jia Guo, Helen H. Lu
Recent advances in the interdisciplinary scientific field of machine perception, computer vision, and biomedical engineering underpin a collection of machine learning algorithms with a remarkable ability to decipher the contents of microscope and nanoscope images.
no code implementations • 6 Nov 2020 • Jia Guo, Chenyang Yang
In this paper, we show that the power control policy has a combination of different PI and PE properties, and existing HetGNN does not satisfy these properties.
no code implementations • 23 Mar 2021 • Jia Guo, Michael E. Kepler, Sai Tej Paruchuri, Haoran Wang, Andrew J. Kurdila, Daniel J. Stilwell
Approximations of the evolution of the ideal local estimate $\hat{g}^i_t$ of agent $i$ is constructed solely using observations made by agent $i$ on a fine time scale.
no code implementations • 3 Aug 2020 • Yilun Zhao, Jia Guo
The performance of MusiCoder is evaluated in two downstream music annotation tasks.
no code implementations • 10 Apr 2021 • Nanyan Zhu, Chen Liu, Xinyang Feng, Dipika Sikka, Sabrina Gjerswold-Selleck, Scott A. Small, Jia Guo
Here we propose a potential solution by first learning a structural-to-functional transformation in brain MRI, and further synthesizing spatially matched functional images from large-scale structural scans.
no code implementations • CVPR 2021 • Jiankang Deng, Jia Guo, Jing Yang, Alexandros Lattas, Stefanos Zafeiriou
Deep face recognition has achieved remarkable improvements due to the introduction of margin-based softmax loss, in which the prototype stored in the last linear layer represents the center of each class.
no code implementations • 16 Aug 2021 • Zheng Zhu, Guan Huang, Jiankang Deng, Yun Ye, JunJie Huang, Xinze Chen, Jiagang Zhu, Tian Yang, Jia Guo, Jiwen Lu, Dalong Du, Jie zhou
There are second phase of the challenge till October 1, 2021 and on-going leaderboard.
no code implementations • 29 Sep 2021 • Jia Guo
Based on this observation, we found that the sharpness gap between the teacher and student output may cause this degradation problem.
no code implementations • 12 Feb 2022 • Ramy Hussein, Moss Zhao, David Shin, Jia Guo, Kevin T. Chen, Rui D. Armindo, Guido Davidzon, Michael Moseley, Greg Zaharchuk
Accurate quantification of cerebral blood flow (CBF) is essential for the diagnosis and assessment of cerebrovascular diseases such as Moyamoya, carotid stenosis, aneurysms, and stroke.
no code implementations • 10 Mar 2022 • Nathan Powell, Bowei Liu, Jia Guo, Sai Tej Parachuri, Andrew J. Kurdila
It is assumed that motions are supported on a low-dimensional, unknown configuration manifold $Q$ that is regularly embedded in high dimensional Euclidean space $X:=\mathbb{R}^d$.
no code implementations • 28 May 2022 • Jinli Liao, Yikang Ding, Yoli Shavit, Dihe Huang, Shihao Ren, Jia Guo, Wensen Feng, Kai Zhang
In this work, we propose Window-based Transformers (WT) for local feature matching and global feature aggregation in multi-view stereo.
no code implementations • 26 Jun 2022 • Junhao Zhang, Vishwanatha M. Rao, Ye Tian, Yanting Yang, Nicolas Acosta, Zihan Wan, Pin-Yu Lee, Chloe Zhang, Lawrence S. Kegeles, Scott A. Small, Jia Guo
Our finding corroborates that schizophrenia is associated with widespread alterations in subcortical brain structure and the subcortical structural information provides prominent features in diagnostic classification.
no code implementations • 24 Oct 2022 • Jia Guo, Haifeng Wang, Chenping Hou
We point out that it is not sufficient to only consider the residual loss in adaptive sampling and sampling should obey temporal causality.
no code implementations • 22 Nov 2022 • Ramy Hussein, David Shin, Moss Zhao, Jia Guo, Guido Davidzon, Michael Moseley, Greg Zaharchuk
Such methods may enable more widespread and accurate CBF evaluation in larger cohorts who cannot undergo PET imaging due to radiation concerns, lack of access, or logistic challenges.
no code implementations • 27 Nov 2022 • Baichuan Zhao, Jia Guo, Chenyang Yang
Learning-based precoding has been shown able to be implemented in real-time, jointly optimized with channel acquisition, and robust to imperfect channels.
no code implementations • 1 Dec 2022 • Jia Guo, Chenyang Yang
Simulation results show that the proposed GNN can well learn spectral efficient and energy efficient precoding policies in single- and multi-cell multi-user multi-antenna systems with low training complexity, and can be well generalized to the numbers of users.
no code implementations • 7 Apr 2023 • Gongning Luo, Kuanquan Wang, Jun Liu, Shuo Li, Xinjie Liang, Xiangyu Li, Shaowei Gan, Wei Wang, Suyu Dong, Wenyi Wang, Pengxin Yu, Enyou Liu, Hongrong Wei, Na Wang, Jia Guo, Huiqi Li, Zhao Zhang, Ziwei Zhao, Na Gao, Nan An, Ashkan Pakzad, Bojidar Rangelov, Jiaqi Dou, Song Tian, Zeyu Liu, Yi Wang, Ampatishan Sivalingam, Kumaradevan Punithakumar, Zhaowen Qiu, Xin Gao
Efficient automatic segmentation of multi-level (i. e. main and branch) pulmonary arteries (PA) in CTPA images plays a significant role in clinical applications.
no code implementations • 24 Jul 2023 • Yao Peng, Jia Guo, Chenyang Yang
We find that the expressive power of the GNNs depends on the linearity and output dimensions of the processing and combination functions.
no code implementations • 8 Dec 2023 • Anbo Cao, Pin-Yu Le, Zhonghui Qie, Haseeb Hassan, Yingwei Guo, Asim Zaman, Jiaxi Lu, Xueqiang Zeng, Huihui Yang, Xiaoqiang Miao, Taiyu Han, Guangtao Huang, Yan Kang, Yu Luo, Jia Guo
The results indicate that the network can accurately estimate perfusion parameters, including cerebral blood volume (CBV), cerebral blood flow (CBF), and time to maximum of the residual function (Tmax).
no code implementations • 13 Dec 2023 • Zhuoyao Xin, Christopher Wu, Dong Liu, Chunming Gu, Jia Guo, Jun Hua
Image segmentation, real-value prediction, and cross-modal translation are critical challenges in medical imaging.
no code implementations • 13 Dec 2023 • Aaron Cao, Vishwanatha M. Rao, Kejia Liu, Xinru Liu, Andrew F. Laine, Jia Guo
Subcortical segmentation remains challenging despite its important applications in quantitative structural analysis of brain MRI scans.
no code implementations • 18 Dec 2023 • Yanting Yang, Jeffery Siyuan Tian, Matthieu Dagommer, Jia Guo
The AFT-Net can be readily used to solve the image inverse problems in domain-transform, especially for accelerated magnetic resonance imaging (MRI) reconstruction and other applications.
no code implementations • 28 Feb 2024 • Jia Guo, Chenyang Yang
Then, we design size-generalizable GNNs that are with these key characteristics and satisfy the PE properties of precoding policies in a recursive manner.
no code implementations • 20 Mar 2024 • Siying Cui, Jia Guo, Xiang An, Jiankang Deng, Yongle Zhao, Xinyu Wei, Ziyong Feng
Leveraging Stable Diffusion for the generation of personalized portraits has emerged as a powerful and noteworthy tool, enabling users to create high-fidelity, custom character avatars based on their specific prompts.
no code implementations • 31 Mar 2024 • Jia Guo, Haonan Han, Shuai Lu, Weihang Zhang, Huiqi Li
We propose Class-Agnostic Distribution Alignment (CADA) to align the mismatched score distribution of each implicit class without knowing class information, which enables unified anomaly detection for all classes and samples.