no code implementations • 11 Oct 2023 • Amin Dada, Aokun Chen, Cheng Peng, Kaleb E Smith, Ahmad Idrissi-Yaghir, Constantin Marc Seibold, Jianning Li, Lars Heiliger, Xi Yang, Christoph M. Friedrich, Daniel Truhn, Jan Egger, Jiang Bian, Jens Kleesiek, Yonghui Wu
Traditionally, large language models have been either trained on general web crawls or domain-specific data.
We evaluated the transfer learning ability of the prompt-based learning algorithms in a cross-institution setting.
This paper targets a novel trade-off problem in generalizable prompt learning for vision-language models (VLM), i. e., improving the performance on unseen classes while maintaining the performance on seen classes.
Scene Text Image Super-resolution (STISR) aims to recover high-resolution (HR) scene text images with visually pleasant and readable text content from the given low-resolution (LR) input.
1 code implementation • 5 Jul 2023 • Nicholas Heller, Fabian Isensee, Dasha Trofimova, Resha Tejpaul, Zhongchen Zhao, Huai Chen, Lisheng Wang, Alex Golts, Daniel Khapun, Daniel Shats, Yoel Shoshan, Flora Gilboa-Solomon, Yasmeen George, Xi Yang, Jianpeng Zhang, Jing Zhang, Yong Xia, Mengran Wu, Zhiyang Liu, Ed Walczak, Sean McSweeney, Ranveer Vasdev, Chris Hornung, Rafat Solaiman, Jamee Schoephoerster, Bailey Abernathy, David Wu, Safa Abdulkadir, Ben Byun, Justice Spriggs, Griffin Struyk, Alexandra Austin, Ben Simpson, Michael Hagstrom, Sierra Virnig, John French, Nitin Venkatesh, Sarah Chan, Keenan Moore, Anna Jacobsen, Susan Austin, Mark Austin, Subodh Regmi, Nikolaos Papanikolopoulos, Christopher Weight
Overall KiTS21 facilitated a significant advancement in the state of the art in kidney tumor segmentation, and provides useful insights that are applicable to the field of semantic segmentation as a whole.
Synthesising a text-to-image model of high-quality images by guiding the generative model through the Text description is an innovative and challenging task.
We then design a novel patch-wise residual module in the anomaly learning head to extract and assess the fine-grained anomaly features from each sample, facilitating the learning of discriminative representations of anomaly instances.
1 code implementation • 22 May 2023 • Cheng Peng, Xi Yang, Aokun Chen, Kaleb E Smith, Nima PourNejatian, Anthony B Costa, Cheryl Martin, Mona G Flores, Ying Zhang, Tanja Magoc, Gloria Lipori, Duane A Mitchell, Naykky S Ospina, Mustafa M Ahmed, William R Hogan, Elizabeth A Shenkman, Yi Guo, Jiang Bian, Yonghui Wu
This study provides insights on the opportunities and challenges of LLMs for medical research and healthcare.
By comparing the similarity between the original text and the generated re-answered text, it can be determined whether the text is machine-generated.
In this work, we study sensing-aided uplink transmission in an integrated sensing and communication (ISAC) vehicular network with the use of orthogonal time frequency space (OTFS) modulation.
Apprenticeship learning (AL) is a process of inducing effective decision-making policies via observing and imitating experts' demonstrations.
To allow third-parties to autonomously inject watermarks into generated text, we develop a watermarking framework for black-box language model usage scenarios.
The archaeological dating of bronze dings has played a critical role in the study of ancient Chinese history.
In this work, students were trained on a logic tutor that supports a default forward-chaining (FC) and a backward-chaining (BC) strategy.
GatorTron-MRC achieves the best strict and lenient F1-scores for concept extraction, outperforming previous deep learning models on the two datasets by 1%~3% and 0. 7%~1. 3%, respectively.
Materials and methods: We developed NLP systems for medication mention extraction, event classification (indicating medication changes discussed or not), and context classification to classify medication changes context into 5 orthogonal dimensions related to drug changes.
Current 3D instance segmentation models generally use multi-stage methods to extract instance objects, including clustering, feature extraction, and post-processing processes.
To further improve the estimation accuracy, we propose a parameter-instance transfer learning approach to transfer the channel knowledge learned from the high-density pilots pre-acquired during the training dataset collection period.
Benefiting from its single-photon sensitivity, single-photon avalanche diode (SPAD) array has been widely applied in various fields such as fluorescence lifetime imaging and quantum computing.
On the one hand, the unidirectional projection enforces our model focused more on the core task, i. e., 3D segmentation; on the other hand, unlocking the bidirectional to unidirectional projection enables a deeper cross-domain semantic alignment and enjoys the flexibility to fuse better and complicated features from very different spaces.
We propose an interactive editing method that allows humans to help deep neural networks (DNNs) learn a latent space more consistent with human knowledge, thereby improving classification accuracy on indistinguishable ambiguous data.
no code implementations • 6 Dec 2022 • Zehao Yu, Xi Yang, Chong Dang, Prakash Adekkanattu, Braja Gopal Patra, Yifan Peng, Jyotishman Pathak, Debbie L. Wilson, Ching-Yuan Chang, Wei-Hsuan Lo-Ciganic, Thomas J. George, William R. Hogan, Yi Guo, Jiang Bian, Yonghui Wu
Objective: We aim to develop an open-source natural language processing (NLP) package, SODA (i. e., SOcial DeterminAnts), with pre-trained transformer models to extract social determinants of health (SDoH) for cancer patients, examine the generalizability of SODA to a new disease domain (i. e., opioid use), and evaluate the extraction rate of SDoH using cancer populations.
no code implementations • 30 Nov 2022 • Mark Harfouche, Kanghyun Kim, Kevin C. Zhou, Pavan Chandra Konda, Sunanda Sharma, Eric E. Thomson, Colin Cooke, Shiqi Xu, Lucas Kreiss, Amey Chaware, Xi Yang, Xing Yao, Vinayak Pathak, Martin Bohlen, Ron Appel, Aurélien Bègue, Clare Cook, Jed Doman, John Efromson, Gregor Horstmeyer, Jaehee Park, Paul Reamey, Veton Saliu, Eva Naumann, Roarke Horstmeyer
This article experimentally examines different configurations of a novel multi-camera array microscope (MCAM) imaging technology.
However, it is difficult to draw a proper scene graph for image retrieval, image generation, and multi-modal applications.
Single-source domain generalization (SDG) in medical image segmentation is a challenging yet essential task as domain shifts are quite common among clinical image datasets.
Generating consistent and high-quality images from given texts is essential for visual-language understanding.
While exogenous variables have a major impact on performance improvement in time series analysis, inter-series correlation and time dependence among them are rarely considered in the present continuous methods.
Due to the uneven distribution of offset points, these existing methods can hardly cluster all instance points.
Ranked #3 on 3D Instance Segmentation on S3DIS
Although deep-learning based methods for monocular pedestrian detection have made great progress, they are still vulnerable to heavy occlusions.
Ranked #1 on Multiview Detection on Wildtrack (using extra training data)
Image outpainting, which is well studied with Convolution Neural Network (CNN) based framework, has recently drawn more attention in computer vision.
As a promising approach in model compression, knowledge distillation improves the performance of a compact model by transferring the knowledge from a cumbersome one.
Attention guidance is an approach to addressing dataset bias in deep learning, where the model relies on incorrect features to make decisions.
This combination of global and local alignment can precisely localize the crucial regions in segmentation target while preserving the overall semantic consistency.
We report Tensorial Tomographic Differential Phase-Contrast microscopy (T2DPC), a quantitative label-free tomographic imaging method for simultaneous measurement of phase and anisotropy.
We consider the problem of Multi-view 3D Face Reconstruction (MVR) with weakly supervised learning that leverages a limited number of 2D face images (e. g. 3) to generate a high-quality 3D face model with very light annotation.
no code implementations • 4 Apr 2022 • Shiqi Xu, Wenhui Liu, Xi Yang, Joakim Jönsson, Ruobing Qian, Paul McKee, Kanghyun Kim, Pavan Chandra Konda, Kevin C. Zhou, Lucas Kreiß, Haoqian Wang, Edouard Berrocal, Scott Huettel, Roarke Horstmeyer
We evaluate our setup by classifying different spatiotemporal-decorrelating patterns hidden beneath a 5mm tissue-like phantom made with rapidly decorrelating dynamic scattering media.
In this paper, we learn an Adaptive Confidence Margin (Ada-CM) to fully leverage all unlabeled data for semi-supervised deep facial expression recognition.
Denoising and demosaicking are two essential steps to reconstruct a clean full-color image from the raw data.
no code implementations • 2 Feb 2022 • Xi Yang, Aokun Chen, Nima PourNejatian, Hoo Chang Shin, Kaleb E Smith, Christopher Parisien, Colin Compas, Cheryl Martin, Mona G Flores, Ying Zhang, Tanja Magoc, Christopher A Harle, Gloria Lipori, Duane A Mitchell, William R Hogan, Elizabeth A Shenkman, Jiang Bian, Yonghui Wu
GatorTron models scale up the clinical language model from 110 million to 8. 9 billion parameters and improve 5 clinical NLP tasks (e. g., 9. 6% and 9. 5% improvement in accuracy for NLI and MQA), which can be applied to medical AI systems to improve healthcare delivery.
In this paper, we develop a novel transformer-based generative adversarial neural network called U-Transformer for generalised image outpainting problem.
Tracing text provenance can help claim the ownership of text content or identify the malicious users who distribute misleading content like machine-generated fake news.
In this study, we examined two state-of-the-art transformer-based NLP models, including BERT and RoBERTa, to extract SBDoH concepts from clinical narratives, applied the best performing model to extract SBDoH concepts on a lung cancer screening patient cohort, and examined the difference of SBDoH information between NLP extracted results and structured EHRs (SBDoH information captured in standard vocabularies such as the International Classification of Diseases codes).
The goal of this study is to systematically explore three widely used transformer-based models (i. e., BERT, RoBERTa, and XLNet) for clinical relation extraction and develop an open-source package with clinical pre-trained transformer-based models to facilitate information extraction in the clinical domain.
Specifically, we first segment the point clouds into parts, and then leverage optimal transport method to match parts and words in an optimized feature space, where each part is represented by aggregating features of all points within it and each word is abstracted by its contextual information.
no code implementations • 3 Jul 2021 • Shiqi Xu, Xi Yang, Wenhui Liu, Joakim Jonsson, Ruobing Qian, Pavan Chandra Konda, Kevin C. Zhou, Lucas Kreiss, Qionghai Dai, Haoqian Wang, Edouard Berrocal, Roarke Horstmeyer
Noninvasive optical imaging through dynamic scattering media has numerous important biomedical applications but still remains a challenging task.
Whole-brain surface extraction is an essential topic in medical imaging systems as it provides neurosurgeons with a broader view of surgical planning and abnormality detection.
For measuring the strength of visually-observed subpopulation differences, the Population Difference Criterion is proposed to assess the statistical significance of visually observed subpopulation differences.
Visible infrared person re-identification (VI-REID) aims to match pedestrian images between the daytime visible and nighttime infrared camera views.
Existing VSR methods are mostly trained and evaluated on synthetic datasets, where the LR videos are uniformly downsampled from their high-resolution (HR) counterparts by some simple operators (e. g., bicubic downsampling).
An approximated ergodic spectral efficiency of the SAoS aided system is derived and the performance impact of the SAoS design is evaluated.
Information Theory Information Theory
We propose a continuous neural network architecture, termed Explainable Tensorized Neural Ordinary Differential Equations (ETN-ODE), for multi-step time series prediction at arbitrary time points.
To fill this gap, in this work we propose a novel and efficient bike station-level prediction algorithm called AtCoR, which can predict the bike usage at both existing and new stations (candidate locations during reconfiguration).
Preterm labor is the leading cause of neonatal morbidity and mortality and has attracted research efforts from many scientific areas.
In this study, we offer a two-step surface-based deep learning pipeline that achieves significantly higher performance.
To improve the visual quality of underwater images, we proposed a novel enhancement model, which is a trainable end-to-end neural model.
In this paper, the correlation between nearby user equipment (UE) is exploited, and a deep learning-based channel state information (CSI) feedback and cooperative recovery framework, CoCsiNet, is developed to reduce feedback overhead.
Information Theory Signal Processing Information Theory
In this paper, instead of 2D medical images, we introduce an open-access 3D intracranial aneurysm dataset, IntrA, that makes the application of points-based and mesh-based classification and segmentation models available.
The WA data can be naturally obtained in an interactive way for specific tasks, for example, in the case of homography estimation, one can easily annotate points on the same plane/object with a single label by observing the image.
Early detection of cancer patients at risk for cardiotoxicity before cardiotoxic treatments and providing preventive measures are potential solutions to improve cancer patients's quality of life.
Deep neural networks (DNNs) have a high accuracy on image classification tasks.
In this paper, the focus is to develop a robust synthetic minority oversampling technique which falls the umbrella of data level approaches.
In this paper, we aim to explore a new search method for images captured with circular fisheye lens, especially the aurora images.