Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Rouhsedaghat, Mozhdeh"'
Autor:
Monajatipoor, Masoud, Yang, Jiaxin, Stremmel, Joel, Emami, Melika, Mohaghegh, Fazlolah, Rouhsedaghat, Mozhdeh, Chang, Kai-Wei
Large Language Models (LLMs) demonstrate remarkable versatility in various NLP tasks but encounter distinct challenges in biomedical due to the complexities of language and data scarcity. This paper investigates LLMs application in the biomedical dom
Externí odkaz:
http://arxiv.org/abs/2404.07376
Autor:
Monajatipoor, Masoud, Li, Liunian Harold, Rouhsedaghat, Mozhdeh, Yang, Lin F., Chang, Kai-Wei
Large-scale language models have shown the ability to adapt to a new task via conditioning on a few demonstrations (i.e., in-context learning). However, in the vision-language domain, most large-scale pre-trained vision-language (VL) models do not po
Externí odkaz:
http://arxiv.org/abs/2306.01311
We offer a method for one-shot mask-guided image synthesis that allows controlling manipulations of a single image by inverting a quasi-robust classifier equipped with strong regularizers. Our proposed method, entitled MAGIC, leverages structured gra
Externí odkaz:
http://arxiv.org/abs/2209.11549
Autor:
Monajatipoor, Masoud, Rouhsedaghat, Mozhdeh, Li, Liunian Harold, Chien, Aichi, Kuo, C. -C. Jay, Scalzo, Fabien, Chang, Kai-Wei
Vision-and-language(V&L) models take image and text as input and learn to capture the associations between them. Prior studies show that pre-trained V&L models can significantly improve the model performance for downstream tasks such as Visual Questi
Externí odkaz:
http://arxiv.org/abs/2108.04938
Autor:
Chen, Hong-Shuo, Rouhsedaghat, Mozhdeh, Ghani, Hamza, Hu, Shuowen, You, Suya, Kuo, C. -C. Jay
A light-weight high-performance Deepfake detection method, called DefakeHop, is proposed in this work. State-of-the-art Deepfake detection methods are built upon deep neural networks. DefakeHop extracts features automatically using the successive sub
Externí odkaz:
http://arxiv.org/abs/2103.06929
Successive Subspace Learning (SSL) offers a light-weight unsupervised feature learning method based on inherent statistical properties of data units (e.g. image pixels and points in point cloud sets). It has shown promising results, especially on sma
Externí odkaz:
http://arxiv.org/abs/2103.00121
A non-parametric low-resolution face recognition model for resource-constrained environments with limited networking and computing is proposed in this work. Such environments often demand a small model capable of being effectively trained on a small
Externí odkaz:
http://arxiv.org/abs/2011.11674
A light-weight low-resolution face gender classification method, called FaceHop, is proposed in this research. We have witnessed rapid progress in face gender classification accuracy due to the adoption of deep learning (DL) technology. Yet, DL-based
Externí odkaz:
http://arxiv.org/abs/2007.09510
The successive subspace learning (SSL) principle was developed and used to design an interpretable learning model, known as the PixelHop method,for image classification in our prior work. Here, we propose an improved PixelHop method and call it Pixel
Externí odkaz:
http://arxiv.org/abs/2002.03141
Publikováno v:
In Pattern Recognition Letters September 2021 149:193-199
