1 code implementation • 20 Mar 2023 • Ligong Han, Yinxiao Li, Han Zhang, Peyman Milanfar, Dimitris Metaxas, Feng Yang
Diffusion models have achieved remarkable success in text-to-image generation, enabling the creation of high-quality images from text prompts or other modalities.
no code implementations • 8 Dec 2022 • Kunpeng Song, Ligong Han, Bingchen Liu, Dimitris Metaxas, Ahmed Elgammal
Can a text-to-image diffusion model be used as a training objective for adapting a GAN generator to another domain?
1 code implementation • 8 Dec 2022 • Zhixing Zhang, Ligong Han, Arnab Ghosh, Dimitris Metaxas, Jian Ren
We propose a novel model-based guidance built upon the classifier-free guidance so that the knowledge from the model trained on a single image can be distilled into the pre-trained diffusion model, enabling content creation even with one given image.
1 code implementation • 16 Sep 2022 • Ananya Jana, Hrebesh Molly Subhash, Dimitris Metaxas
We conclude that the segmentation methods can learn a great deal of information from a single 3D tooth point cloud scan under suitable conditions e. g. data augmentation.
1 code implementation • 18 Jul 2022 • Shiyu Zhao, Zhixing Zhang, Samuel Schulter, Long Zhao, Vijay Kumar B. G, Anastasis Stathopoulos, Manmohan Chandraker, Dimitris Metaxas
We propose a novel method that leverages the rich semantics available in recent vision and language models to localize and classify objects in unlabeled images, effectively generating pseudo labels for object detection.
Ranked #6 on
Open Vocabulary Object Detection
on MSCOCO
(using extra training data)
no code implementations • 18 Jun 2022 • Zachary A Daniels, Dimitris Metaxas
Suppose that an agent utilizing one or more sensors is placed in an unknown environment, and based on its sensory input, the agent needs to assign some label to the perceived scene.
no code implementations • 14 Jun 2022 • Qi Chang, Zhennan Yan, Mu Zhou, Di Liu, Khalid Sawalha, Meng Ye, Qilong Zhangli, Mikael Kanski, Subhi Al Aref, Leon Axel, Dimitris Metaxas
Joint 2D cardiac segmentation and 3D volume reconstruction are fundamental to building statistical cardiac anatomy models and understanding functional mechanisms from motion patterns.
no code implementations • 24 Mar 2022 • Wenjia Zhang, Yikai Zhang, Xiaoling Hu, Mayank Goswami, Chao Chen, Dimitris Metaxas
Assuming data lies in a manifold, we investigate two new types of adversarial risk, the normal adversarial risk due to perturbation along normal direction, and the in-manifold adversarial risk due to perturbation within the manifold.
1 code implementation • CVPR 2022 • Shiyu Zhao, Long Zhao, Zhixing Zhang, Enyu Zhou, Dimitris Metaxas
In this paper, inspired by the traditional matching-optimization methods where matching is introduced to handle large displacements before energy-based optimizations, we introduce a simple but effective global matching step before the direct regression and develop a learning-based matching-optimization framework, namely GMFlowNet.
Ranked #3 on
Optical Flow Estimation
on KITTI 2015 (train)
no code implementations • 21 Mar 2022 • Di Liu, Yunhe Gao, Qilong Zhangli, Ligong Han, Xiaoxiao He, Zhaoyang Xia, Song Wen, Qi Chang, Zhennan Yan, Mu Zhou, Dimitris Metaxas
Combining information from multi-view images is crucial to improve the performance and robustness of automated methods for disease diagnosis.
no code implementations • 6 Mar 2022 • Qilong Zhangli, Jingru Yi, Di Liu, Xiaoxiao He, Zhaoyang Xia, Qi Chang, Ligong Han, Yunhe Gao, Song Wen, Haiming Tang, He Wang, Mu Zhou, Dimitris Metaxas
Top-down instance segmentation framework has shown its superiority in object detection compared to the bottom-up framework.
1 code implementation • CVPR 2022 • Ligong Han, Jian Ren, Hsin-Ying Lee, Francesco Barbieri, Kyle Olszewski, Shervin Minaee, Dimitris Metaxas, Sergey Tulyakov
In addition, our model can extract visual information as suggested by the text prompt, e. g., "an object in image one is moving northeast", and generate corresponding videos.
no code implementations • 22 Jan 2022 • Qi Chang, Hui Qu, Zhennan Yan, Yunhe Gao, Lohendran Baskaran, Dimitris Metaxas
Multi-modality images have been widely used and provide comprehensive information for medical image analysis.
1 code implementation • 21 Jan 2022 • Zhuowei Li, Zihao Liu, Zhiqiang Hu, Qing Xia, Ruiqin Xiong, Shaoting Zhang, Dimitris Metaxas, Tingting Jiang
Medical image segmentation has been widely recognized as a pivot procedure for clinical diagnosis, analysis, and treatment planning.
no code implementations • 19 Jan 2022 • Carol Neidle, Augustine Opoku, Dimitris Metaxas
These data have been used for many types of research in linguistics and in computer-based sign language recognition from video; examples of such research are provided in the latter part of this article.
1 code implementation • 17 Oct 2021 • Ligong Han, Sri Harsha Musunuri, Martin Renqiang Min, Ruijiang Gao, Yu Tian, Dimitris Metaxas
StyleGANs have shown impressive results on data generation and manipulation in recent years, thanks to its disentangled style latent space.
1 code implementation • 29 Sep 2021 • Guotai Wang, Shuwei Zhai, Giovanni Lasio, Baoshe Zhang, Byong Yi, Shifeng Chen, Thomas J. Macvittie, Dimitris Metaxas, Jinghao Zhou, Shaoting Zhang
Computed Tomography (CT) plays an important role in monitoring radiation-induced Pulmonary Fibrosis (PF), where accurate segmentation of the PF lesions is highly desired for diagnosis and treatment follow-up.
1 code implementation • 10 Sep 2021 • Ananya Jana, Carlos D. Minacapelli, Vinod Rustgi, Dimitris Metaxas
We explore one of the most recent techniques called symbolic metamodeling to find the mathematical expression of the machine learning models for COVID-19.
1 code implementation • ICCV 2021 • Ligong Han, Martin Renqiang Min, Anastasis Stathopoulos, Yu Tian, Ruijiang Gao, Asim Kadav, Dimitris Metaxas
We then propose an improved cGAN model with Auxiliary Classification that directly aligns the fake and real conditionals $P(\text{class}|\text{image})$ by minimizing their $f$-divergence.
1 code implementation • 2 Jul 2021 • Yunhe Gao, Mu Zhou, Dimitris Metaxas
In this study, we present UTNet, a simple yet powerful hybrid Transformer architecture that integrates self-attention into a convolutional neural network for enhancing medical image segmentation.
1 code implementation • 30 Mar 2021 • Yunhe Gao, Zhiqiang Tang, Mu Zhou, Dimitris Metaxas
Data augmentation has proved extremely useful by increasing training data variance to alleviate overfitting and improve deep neural networks' generalization performance.
1 code implementation • 5 Mar 2021 • Ananya Jana, Hui Qu, Carlos D. Minacapelli, Carolyn Catalano, Vinod Rustgi, Dimitris Metaxas
The severity and treatment of NAFLD is determined by NAFLD Activity Scores (NAS)and liver fibrosis stage, which are usually obtained from liver biopsy.
1 code implementation • CVPR 2021 • Meng Ye, Mikael Kanski, Dong Yang, Qi Chang, Zhennan Yan, Qiaoying Huang, Leon Axel, Dimitris Metaxas
Cardiac tagging magnetic resonance imaging (t-MRI) is the gold standard for regional myocardium deformation and cardiac strain estimation.
1 code implementation • 9 Feb 2021 • Yikai Zhang, Hui Qu, Qi Chang, Huidong Liu, Dimitris Metaxas, Chao Chen
A federatedGAN jointly trains a centralized generator and multiple private discriminators hosted at different sites.
1 code implementation • ICCV 2021 • Zhiqiang Tang, Yunhe Gao, Yi Zhu, Zhi Zhang, Mu Li, Dimitris Metaxas
Can we develop new normalization methods to improve generalization robustness under distribution shifts?
1 code implementation • NeurIPS 2020 • Pengxiang Wu, Songzhu Zheng, Mayank Goswami, Dimitris Metaxas, Chao Chen
Noisy labels can impair the performance of deep neural networks.
1 code implementation • CVPR 2021 • Long Zhao, Yuxiao Wang, Jiaping Zhao, Liangzhe Yuan, Jennifer J. Sun, Florian Schroff, Hartwig Adam, Xi Peng, Dimitris Metaxas, Ting Liu
To evaluate the power of the learned representations, in addition to the conventional fully-supervised action recognition settings, we introduce a novel task called single-shot cross-view action recognition.
no code implementations • NeurIPS 2020 • Mahdi Abavisani, Alireza Naghizadeh, Dimitris Metaxas, Vishal Patel
In particular, we introduce a temporal ensembling component to the objective function of DSC algorithms to enable the DSC networks to maintain consistent subspaces for random transformations in the input data.
3 code implementations • ICML 2020 • Songzhu Zheng, Pengxiang Wu, Aman Goswami, Mayank Goswami, Dimitris Metaxas, Chao Chen
To be robust against label noise, many successful methods rely on the noisy classifiers (i. e., models trained on the noisy training data) to determine whether a label is trustworthy.
Ranked #37 on
Image Classification
on Clothing1M
1 code implementation • NeurIPS 2020 • Long Zhao, Ting Liu, Xi Peng, Dimitris Metaxas
In this paper, we propose a novel and effective regularization term for adversarial data augmentation.
1 code implementation • 22 Sep 2020 • Ananya Jana, Hui Qu, Puru Rattan, Carlos D. Minacapelli, Vinod Rustgi, Dimitris Metaxas
In this work, we propose a novel method to automatically predict NAS score and fibrosis stage from CT data that is non-invasive and inexpensive to obtain compared with liver biopsy.
no code implementations • 25 Aug 2020 • Qiaoying Huang, Eric Z. Chen, Hanchao Yu, Yimo Guo, Terrence Chen, Dimitris Metaxas, Shanhui Sun
We also analyze thickness patterns on different cardiac pathologies with a standard clinical model and the results demonstrate the potential clinical value of our method for thickness based cardiac disease diagnosis.
no code implementations • 19 Aug 2020 • Qiaoying Huang, Dong Yang, Yikun Xian, Pengxiang Wu, Jingru Yi, Hui Qu, Dimitris Metaxas
The accurate reconstruction of under-sampled magnetic resonance imaging (MRI) data using modern deep learning technology, requires significant effort to design the necessary complex neural network architectures.
no code implementations • 18 Aug 2020 • Meng Ye, Qiaoying Huang, Dong Yang, Pengxiang Wu, Jingru Yi, Leon Axel, Dimitris Metaxas
The 3D volumetric shape of the heart's left ventricle (LV) myocardium (MYO) wall provides important information for diagnosis of cardiac disease and invasive procedure navigation.
1 code implementation • 17 Aug 2020 • Jingru Yi, Pengxiang Wu, Bo Liu, Qiaoying Huang, Hui Qu, Dimitris Metaxas
To address this issue, in this work we extend the horizontal keypoint-based object detector to the oriented object detection task.
Ranked #1 on
Object Detection
on DOTA
1 code implementation • ECCV 2020 • Hui Qu, Yikai Zhang, Qi Chang, Zhennan Yan, Chao Chen, Dimitris Metaxas
Our proposed method tackles the challenge of training GAN in the federated learning manner: How to update the generator with a flow of temporary discriminators?
1 code implementation • ECCV 2020 • Zhiqiang Tang, Yunhe Gao, Leonid Karlinsky, Prasanna Sattigeri, Rogerio Feris, Dimitris Metaxas
First is that most if not all modern augmentation search methods are offline and learning policies are isolated from their usage.
1 code implementation • 13 Jun 2020 • Ligong Han, Anastasis Stathopoulos, Tao Xue, Dimitris Metaxas
To remedy this, Twin Auxiliary Classifier GAN (TAC-GAN) introduces a twin classifier to the min-max game.
1 code implementation • CVPR 2020 • Qi Chang, Hui Qu, Yikai Zhang, Mert Sabuncu, Chao Chen, Tong Zhang, Dimitris Metaxas
In this paper, we propose a data privacy-preserving and communication efficient distributed GAN learning framework named Distributed Asynchronized Discriminator GAN (AsynDGAN).
2 code implementations • CVPR 2020 • Pengxiang Wu, Siheng Chen, Dimitris Metaxas
The backbone of MotionNet is a novel spatio-temporal pyramid network, which extracts deep spatial and temporal features in a hierarchical fashion.
no code implementations • 25 Nov 2019 • Pengxiang Wu, Chao Chen, Jingru Yi, Dimitris Metaxas
The spatial layout of the beams is regular, and this allows the beam features to be further fed into an efficient 2D convolutional neural network (CNN) for hierarchical feature aggregation.
1 code implementation • 21 Nov 2019 • Ligong Han, Ruijiang Gao, Mun Kim, Xin Tao, Bo Liu, Dimitris Metaxas
Conditional generative adversarial networks have shown exceptional generation performance over the past few years.
no code implementations • 25 Sep 2019 • Songzhu Zheng, Pengxiang Wu, Aman Goswami, Mayank Goswami, Dimitris Metaxas, Chao Chen
To collect large scale annotated data, it is inevitable to introduce label noise, i. e., incorrect class labels.
1 code implementation • 25 Jul 2019 • Ligong Han, Yang Zou, Ruijiang Gao, Lezi Wang, Dimitris Metaxas
Unsupervised domain adaptation (UDA) aims at inferring class labels for unlabeled target domain given a related labeled source dataset.
no code implementations • 22 Feb 2019 • Xiaoxiao He, Chaowei Tan, Yuting Qiao, Virak Tan, Dimitris Metaxas, Kang Li
For the initial shoulder preoperative diagnosis, it is essential to obtain a three-dimensional (3D) bone mask from medical images, e. g., magnetic resonance (MR).
no code implementations • 5 Dec 2018 • Qiaoying Huang, Xiao Chen, Dimitris Metaxas, Mariappan S. Nadar
The task of medical image segmentation commonly involves an image reconstruction step to convert acquired raw data to images before any analysis.
1 code implementation • 18 Oct 2018 • Qiaoying Huang, Dong Yang, Pengxiang Wu, Hui Qu, Jingru Yi, Dimitris Metaxas
We consider an MRI reconstruction problem with input of k-space data at a very low undersampled rate.
1 code implementation • ECCV 2018 • Zhiqiang Tang, Xi Peng, Shijie Geng, Lingfei Wu, Shaoting Zhang, Dimitris Metaxas
Finally, to reduce the memory consumption and high precision operations both in training and testing, we further quantize weights, inputs, and gradients of our localization network to low bit-width numbers.
Ranked #18 on
Pose Estimation
on MPII Human Pose
1 code implementation • ECCV 2018 • Long Zhao, Xi Peng, Yu Tian, Mubbasir Kapadia, Dimitris Metaxas
We consider the problem of image-to-video translation, where an input image is translated into an output video containing motions of a single object.
1 code implementation • CVPR 2018 • Hareesh Ravi, Lezi Wang, Carlos Muniz, Leonid Sigal, Dimitris Metaxas, Mubbasir Kapadia
We propose an end-to-end network for the visual illustration of a sequence of sentences forming a story.
no code implementations • CVPR 2018 • Xi Peng, Zhiqiang Tang, Fei Yang, Rogerio Feris, Dimitris Metaxas
Random data augmentation is a critical technique to avoid overfitting in training deep neural network models.
Ranked #3 on
Pose Estimation
on Leeds Sports Poses
48 code implementations • arXiv 2018 • Han Zhang, Ian Goodfellow, Dimitris Metaxas, Augustus Odena
In this paper, we propose the Self-Attention Generative Adversarial Network (SAGAN) which allows attention-driven, long-range dependency modeling for image generation tasks.
Ranked #17 on
Conditional Image Generation
on ImageNet 128x128
2 code implementations • ICLR 2018 • Tim Salimans, Han Zhang, Alec Radford, Dimitris Metaxas
We present Optimal Transport GAN (OT-GAN), a variant of generative adversarial nets minimizing a new metric measuring the distance between the generator distribution and the data distribution.
no code implementations • 6 Feb 2018 • Rahil Mehrizi, Xi Peng, Zhiqiang Tang, Xu Xu, Dimitris Metaxas, Kang Li
The results are also compared with state-of-the-art methods on HumanEva-I dataset, which demonstrates the superior performance of our approach.
no code implementations • 2 Dec 2017 • Yan Zhu, Shaoting Zhang, Dimitris Metaxas
In this paper, we introduce an interactive training method to improve the natural language conversation system for a visual grounding task.
16 code implementations • 19 Oct 2017 • Han Zhang, Tao Xu, Hongsheng Li, Shaoting Zhang, Xiaogang Wang, Xiaolei Huang, Dimitris Metaxas
In this paper, we propose Stacked Generative Adversarial Networks (StackGAN) aiming at generating high-resolution photo-realistic images.
Ranked #5 on
Text-to-Image Generation
on Oxford 102 Flowers
no code implementations • 25 Jul 2017 • Dong Yang, Daguang Xu, S. Kevin Zhou, Bogdan Georgescu, Mingqing Chen, Sasa Grbic, Dimitris Metaxas, Dorin Comaniciu
Automatic liver segmentation in 3D medical images is essential in many clinical applications, such as pathological diagnosis of hepatic diseases, surgical planning, and postoperative assessment.
no code implementations • 17 May 2017 • Dong Yang, Tao Xiong, Daguang Xu, Qiangui Huang, David Liu, S. Kevin Zhou, Zhoubing Xu, Jin-Hyeong Park, Mingqing Chen, Trac. D. Tran, Sang Peter Chin, Dimitris Metaxas, Dorin Comaniciu
In this paper, we propose an automatic and fast algorithm to localize and label the vertebra centroids in 3D CT volumes.
no code implementations • ICCV 2017 • Xi Peng, Xiang Yu, Kihyuk Sohn, Dimitris Metaxas, Manmohan Chandraker
Finally, we propose a new feature reconstruction metric learning to explicitly disentangle identity and pose, by demanding alignment between the feature reconstructions through various combinations of identity and pose features, which is obtained from two images of the same subject.
21 code implementations • ICCV 2017 • Han Zhang, Tao Xu, Hongsheng Li, Shaoting Zhang, Xiaogang Wang, Xiaolei Huang, Dimitris Metaxas
Synthesizing high-quality images from text descriptions is a challenging problem in computer vision and has many practical applications.
Ranked #3 on
Text-to-Image Generation
on Oxford 102 Flowers
(Inception score metric)
no code implementations • CVPR 2016 • Han Zhang, Tao Xu, Mohamed Elhoseiny, Xiaolei Huang, Shaoting Zhang, Ahmed Elgammal, Dimitris Metaxas
In this paper, we propose a new CNN architecture that integrates semantic part detection and abstraction (SPDA-CNN) for fine-grained classification.
no code implementations • LREC 2016 • Polina Yanovich, Carol Neidle, Dimitris Metaxas
In American Sign Language (ASL) as well as other signed languages, different classes of signs (e. g., lexical signs, fingerspelled signs, and classifier constructions) have different internal structural properties.
no code implementations • NeurIPS 2014 • Chao Chen, Han Liu, Dimitris Metaxas, Tianqi Zhao
Though the mode finding problem is generally intractable in high dimensions, this paper unveils that, if the distribution can be approximated well by a tree graphical model, mode characterization is significantly easier.
no code implementations • LREC 2014 • Mark Dilsizian, Polina Yanovich, Shu Wang, Carol Neidle, Dimitris Metaxas
Current approaches to sign recognition by computer generally have at least some of the following limitations: they rely on laboratory conditions for sign production, are limited to a small vocabulary, rely on 2D modeling (and therefore cannot deal with occlusions and off-plane rotations), and/or achieve limited success.
no code implementations • LREC 2014 • Bo Liu, Jingjing Liu, Xiang Yu, Dimitris Metaxas, Carol Neidle
Essential grammatical information is conveyed in signed languages by clusters of events involving facial expressions and movements of the head and upper body.
no code implementations • CVPR 2013 • Lin Zhong, Sunghyun Cho, Dimitris Metaxas, Sylvain Paris, Jue Wang
Based on this observation, our method applies a series of directional filters at different orientations to the input image, and estimates an accurate Radon transform of the blur kernel from each filtered image.
no code implementations • 6 Feb 2013 • Fei Yang, Hong Jiang, Zuowei Shen, Wei Deng, Dimitris Metaxas
We address the problem of reconstructing and analyzing surveillance videos using compressive sensing.
no code implementations • LREC 2012 • Dimitris Metaxas, Bo Liu, Fei Yang, Peng Yang, Nicholas Michael, Carol Neidle
This paper addresses the problem of automatically recognizing linguistically significant nonmanual expressions in American Sign Language from video.