1 code implementation • 13 Feb 2024 • Chongyang Gao, Kezhen Chen, Jinmeng Rao, Baochen Sun, Ruibo Liu, Daiyi Peng, Yawen Zhang, Xiaoyuan Guo, Jie Yang, VS Subrahmanian
In this paper, we introduce a novel parameter-efficient MoE method, \textit{\textbf{M}oE-L\textbf{o}RA with \textbf{L}ayer-wise Expert \textbf{A}llocation (MoLA)} for Transformer-based models, where each model layer has the flexibility to employ a varying number of LoRA experts.
no code implementations • 7 Sep 2023 • Jiaying Lu, Jinmeng Rao, Kezhen Chen, Xiaoyuan Guo, Yawen Zhang, Baochen Sun, Carl Yang, Jie Yang
Large Vision-Language Models (LVLMs) offer remarkable benefits for a variety of vision-language tasks.
no code implementations • 19 Aug 2023 • Diji Yang, Kezhen Chen, Jinmeng Rao, Xiaoyuan Guo, Yawen Zhang, Jie Yang, Yi Zhang
Visual language tasks require AI models to comprehend and reason with both visual and textual content.
no code implementations • 31 May 2023 • Xiaoyuan Guo, Kezhen Chen, Jinmeng Rao, Yawen Zhang, Baochen Sun, Jie Yang
To train LOWA, we propose a hybrid vision-language training strategy to learn object detection and recognition with class names as well as attribute information.
no code implementations • 31 Jul 2022 • Xiaoyuan Guo, Jiali Duan, C. -C. Jay Kuo, Judy Wawira Gichoya, Imon Banerjee
Language modality within the vision language pretraining framework is innately discretized, endowing each word in the language vocabulary a semantic meaning.
no code implementations • 6 Apr 2022 • Xiaoyuan Guo, Jiali Duan, Saptarshi Purkayastha, Hari Trivedi, Judy Wawira Gichoya, Imon Banerjee
While existing methods can be applied for class-wise retrieval (aka.
no code implementations • 27 Dec 2021 • Xiaoyuan Guo, Judy Wawira Gichoya, Hari Trivedi, Saptarshi Purkayastha, Imon Banerjee
Given an internal dataset A as the base source, we first train anomaly detectors for each class of dataset A to learn internal distributions in an unsupervised way.
1 code implementation • 29 Oct 2021 • Xiaoyuan Guo, Judy Wawira Gichoya, Saptarshi Purkayastha, Imon Banerjee
The key issue is the granularity of OOD data in the medical domain, where intra-class OOD samples are predominant.
1 code implementation • 31 Jul 2021 • Xiaoyuan Guo, Judy Wawira Gichoya, Saptarshi Purkayastha, Imon Banerjee
Traditional anomaly detection methods focus on detecting inter-class variations while medical image novelty identification is inherently an intra-class detection problem.
no code implementations • 16 Nov 2019 • Xiaoyuan Guo, Fusheng Wang, George Teodorou, Alton B. Farris, Jun Kong
Liver steatosis is known as the abnormal accumulation of lipids within cells.
no code implementations • 14 Aug 2018 • Xiaoyuan Guo, Hanyi Yu, Blair Rossetti, George Teodoro, Daniel Brat, Jun Kong
Highly clumped nuclei clusters captured in fluorescence in situ hybridization microscopy images are common histology entities under investigations in a wide spectrum of tissue-related biomedical investigations.
no code implementations • 5 Jul 2018 • Jiali Duan, Xiaoyuan Guo, Yuhang Song, Chao Yang, C. -C. Jay Kuo
Previous methods have dealt with discrete manipulation of facial attributes such as smile, sad, angry, surprise etc, out of canonical expressions and they are not scalable, operating in single modality.
no code implementations • 21 Nov 2016 • Jiali Duan, Shuai Zhou, Jun Wan, Xiaoyuan Guo, Stan Z. Li
Recently, the popularity of depth-sensors such as Kinect has made depth videos easily available while its advantages have not been fully exploited.