no code implementations • 18 Mar 2024 • Xiangyu Chen, Jing Liu, Ye Wang, Pu, Wang, Matthew Brand, Guanghui Wang, Toshiaki Koike-Akino
Low-rank adaptation (LoRA) and its variants are widely employed in fine-tuning large models, including large language models for natural language processing and diffusion models for computer vision.
no code implementations • 23 Jan 2024 • Nikki Bialy, Frank Alber, Brenda Andrews, Michael Angelo, Brian Beliveau, Lacramioara Bintu, Alistair Boettiger, Ulrike Boehm, Claire M. Brown, Mahmoud Bukar Maina, James J. Chambers, Beth A. Cimini, Kevin Eliceiri, Rachel Errington, Orestis Faklaris, Nathalie Gaudreault, Ronald N. Germain, Wojtek Goscinski, David Grunwald, Michael Halter, Dorit Hanein, John W. Hickey, Judith Lacoste, Alex Laude, Emma Lundberg, Jian Ma, Leonel Malacrida, Josh Moore, Glyn Nelson, Elizabeth Kathleen Neumann, Roland Nitschke, Shuichi Onami, Jaime A. Pimentel, Anne L. Plant, Andrea J. Radtke, Bikash Sabata, Denis Schapiro, Johannes Schöneberg, Jeffrey M. Spraggins, Damir Sudar, Wouter-Michiel Adrien Maria Vierdag, Niels Volkmann, Carolina Wählby, Siyuan, Wang, Ziv Yaniv, Caterina Strambio-De-Castillia
Together with the molecular knowledge of genes and proteins, biological images promise to significantly enhance the scientific understanding of complex cellular systems and to advance predictive and personalized therapeutic products for human health.
1 code implementation • NeurIPS 2023 • Jiayi Shen, XianTong Zhen, QI, Wang, Marcel Worring
This paper focuses on the data-insufficiency problem in multi-task learning within an episodic training setup.
no code implementations • 10 Jul 2023 • Lei LI, Julia Camps, Zhinuo, Wang, Abhirup Banerjee, Marcel Beetz, Blanca Rodriguez, Vicente Grau
In this work, we investigate the feasibility of inferring myocardial tissue properties from the electrocardiogram (ECG) within a CDT platform.
no code implementations • 4 Jul 2023 • Yong Zheng, Kumar Neelotpal Shukla, Jasmine Xu, David, Wang, Michael O'Leary
MOPO-LSI is an open-source Multi-Objective Portfolio Optimization Library for Sustainable Investments.
no code implementations • 4 May 2023 • Hou, Sujuan, Xingzhuo, Min, Weiqing, Li, Jiacheng, Wang, Jing, Zheng, Yuanjie, Jiang, Shuqiang
The aggregation of small logos also brings a great challenge to the classification and localization of logos.
no code implementations • 4 Apr 2023 • Lei LI, Julia Camps, Zhinuo, Wang, Abhirup Banerjee, Blanca Rodriguez, Vicente Grau
However, the influence of various MI properties on the QRS is not intuitively predictable. In this work, we have systematically investigated the effects of 17 post-MI scenarios, varying the location, size, transmural extent, and conductive level of scarring and border zone area, on the forward-calculated QRS.
no code implementations • 21 Jan 2023 • Huancheng Chen, Johnny, Wang, Haris Vikalo
In particular, each client extracts and sends to the server the means of local data representations and the corresponding soft predictions -- information that we refer to as ``hyper-knowledge".
1 code implementation • 20 Dec 2022 • Jason Li, Nicholas Watters, Yingting, Wang, Hansem Sohn, Mehrdad Jazayeri
This not only provides a generative model of eye movements in this task but also suggests a computational theory for how humans solve the task, namely that humans use mental simulation.
no code implementations • 20 Sep 2022 • Haifeng Xia, Pu, Wang, Toshiaki Koike-Akino, Ye Wang, Philip Orlik, Zhengming Ding
Domain adaptation (DA) aims to transfer the knowledge of a well-labeled source domain to facilitate unlabeled target learning.
no code implementations • 9 May 2022 • Yan-Ran, Wang, Liangqiong Qu, Natasha Diba Sheybani, Xiaolong Luo, Jiangshan Wang, Kristina Elizabeth Hawk, Ashok Joseph Theruvath, Sergios Gatidis, Xuerong Xiao, Allison Pribnow, Daniel Rubin, Heike E. Daldrup-Link
In this study, we utilize the global similarity between baseline and follow-up PET and magnetic resonance (MR) images to develop Masked-LMCTrans, a longitudinal multi-modality co-attentional CNN-Transformer that provides interaction and joint reasoning between serial PET/MRs of the same patient.
no code implementations • 28 Mar 2022 • Zhijian Wang, Shujie Zhou, Qinmei Yao, Yijia, Wang
Game dynamics theory, as a field of science, the consistency of theory and experiment is essential.
no code implementations • 19 Feb 2022 • Jianyuan Yu, Pu, Wang, Toshiaki Koike-Akino, Philip V. Orlik
This paper considers indoor localization using multi-modal wireless signals including Wi-Fi, inertial measurement unit (IMU), and ultra-wideband (UWB).
no code implementations • 28 Dec 2021 • Jianyuan Yu, Pu, Wang, Toshiaki Koike-Akino, Ye Wang, Philip V. Orlik, R. Michael Buehrer
The granularity matching is realized by pairing two feature maps from the CSI and beam SNR at different granularity levels and linearly combining all paired feature maps into a fused feature map with learnable weights.
1 code implementation • 10 Sep 2021 • Wenbin Li, Ziyi, Wang, Xuesong Yang, Chuanqi Dong, Pinzhuo Tian, Tiexin Qin, Jing Huo, Yinghuan Shi, Lei Wang, Yang Gao, Jiebo Luo
Furthermore, based on LibFewShot, we provide comprehensive evaluations on multiple benchmarks with various backbone architectures to evaluate common pitfalls and effects of different training tricks.
1 code implementation • ICIP 2021 • Wang, Qian; Breckon, Toby P.
The outlier classes can be detected if no target-domain data are labeled as these classes.
Ranked #2 on Partial Domain Adaptation on Office-31
no code implementations • 13 Aug 2021 • Yong Zheng, David, Wang
Recommender systems (RecSys) have been well developed to assist user decision making.
no code implementations • 17 Mar 2021 • Boxiang Dong, Hui, Wang, Aparna S. Varde, Dawei Li, Bharath K. Samanthula, Weifeng Sun, Liang Zhao
To achieve high detection accuracy on imbalanced data, we design a novel attack-sharing loss function that can effectively move the decision boundary towards the attack classes and eliminates the bias towards the majority/benign class.
1 code implementation • IEEE Spoken Language Technology Workshop (SLT) 2021 • Wang, Pu; Van hamme, Hugo
Spoken language understanding (SLU) systems can make life more agreeable, safer (e. g. in a car) or can increase the independence of physically challenged users.
no code implementations • 16 Jan 2020 • Vansh Narula, Zhangyang, Wang, Theodora Chaspari
Image and video-capturing technologies have permeated our every-day life.
no code implementations • 4 Dec 2019 • Alexandre Belloni, Mingli Chen, Oscar Hernan Madrid Padilla, Zixuan, Wang
We propose a generalization of the linear panel quantile regression model to accommodate both \textit{sparse} and \textit{dense} parts: sparse means while the number of covariates available is large, potentially only a much smaller number of them have a nonzero impact on each conditional quantile of the response variable; while the dense part is represent by a low-rank matrix that can be approximated by latent factors and their loadings.
no code implementations • 14 Oct 2019 • Derui, Wang, Chaoran Li, Sheng Wen, Surya Nepal, Yang Xiang
First, such attacks must acquire the outputs from the models by multiple times before actually launching attacks, which is difficult for the MitM adversary in practice.
no code implementations • 26 Jul 2019 • Junyu, Wang, Rong Song
Single image super-resolution (SISR) is a very popular topic nowadays, which has both research value and practical value.
no code implementations • ISARC. Proceedings of the International Symposium on Automation and Robotics in Construction 2019 • Wang, Ruoyu; Xiang, Siyuan; Feng, Chen; Wang, Pu; Ergan, Semiha; Yi Fang
Yet unlike optical images, RF images are difficult to understand by a human.
no code implementations • 20 Jul 2018 • Seyed shahabeddin Nabavi, Mrigank Rochan, Yang, Wang
We propose a novel model that uses convolutional LSTM (ConvLSTM) to encode the spatiotemporal information of observed frames for future prediction.
1 code implementation • ICASSP 2018 • Wang, Z.-Q.; Le Roux, J.; Hershey, J.R
The recently proposed deep clustering framework represents a significant step towards solv-ing the cocktail party problem.
Ranked #29 on Speech Separation on WSJ0-2mix
no code implementations • 24 Sep 2015 • Yi, Wang, Guangliang Chen, Mauro Maggioni
We briefly review recent progress in techniques for modeling and analyzing hyperspectral images and movies, in particular for detecting plumes of both known and unknown chemicals.