Zobrazeno 1 - 10
of 48
pro vyhledávání: '"Lin, Rongmei"'
Autor:
Cui, Hejie, Lin, Rongmei, Zalmout, Nasser, Zhang, Chenwei, Shang, Jingbo, Yang, Carl, Li, Xian
Information extraction, e.g., attribute value extraction, has been extensively studied and formulated based only on text. However, many attributes can benefit from image-based extraction, like color, shape, pattern, among others. The visual modality
Externí odkaz:
http://arxiv.org/abs/2306.01016
Autor:
Lin, Rongmei, Xiao, Yonghui, Yang, Tien-Ju, Zhao, Ding, Xiong, Li, Motta, Giovanni, Beaufays, Françoise
Automatic Speech Recognition models require large amount of speech data for training, and the collection of such data often leads to privacy concerns. Federated learning has been widely used and is considered to be an effective decentralized techniqu
Externí odkaz:
http://arxiv.org/abs/2209.06359
Understanding product attributes plays an important role in improving online shopping experience for customers and serves as an integral part for constructing a product knowledge graph. Most existing methods focus on attribute extraction from text de
Externí odkaz:
http://arxiv.org/abs/2106.04630
Due to the over-parameterization nature, neural networks are a powerful tool for nonlinear function approximation. In order to achieve good generalization on unseen data, a suitable inductive bias is of great importance for neural networks. One of th
Externí odkaz:
http://arxiv.org/abs/2103.01649
Autor:
Liu, Weiyang, Lin, Rongmei, Liu, Zhen, Rehg, James M., Paull, Liam, Xiong, Li, Song, Le, Weller, Adrian
The inductive bias of a neural network is largely determined by the architecture and the training algorithm. To achieve good generalization, how to effectively train a neural network is of great importance. We propose a novel orthogonal over-paramete
Externí odkaz:
http://arxiv.org/abs/2004.04690
Autor:
Lin, Rongmei, Liu, Weiyang, Liu, Zhen, Feng, Chen, Yu, Zhiding, Rehg, James M., Xiong, Li, Song, Le
Inspired by the Thomson problem in physics where the distribution of multiple propelling electrons on a unit sphere can be modeled via minimizing some potential energy, hyperspherical energy minimization has demonstrated its potential in regularizing
Externí odkaz:
http://arxiv.org/abs/1906.04892
Neural networks are a powerful class of nonlinear functions that can be trained end-to-end on various applications. While the over-parametrization nature in many neural networks renders the ability to fit complex functions and the strong representati
Externí odkaz:
http://arxiv.org/abs/1805.09298
In this paper we propose novel Deformable Part Networks (DPNs) to learn {\em pose-invariant} representations for 2D object recognition. In contrast to the state-of-the-art pose-aware networks such as CapsNet \cite{sabour2017dynamic} and STN \cite{jad
Externí odkaz:
http://arxiv.org/abs/1805.08808
Autor:
Liu, Weiyang, Liu, Zhen, Yu, Zhiding, Dai, Bo, Lin, Rongmei, Wang, Yisen, Rehg, James M., Song, Le
Inner product-based convolution has been a central component of convolutional neural networks (CNNs) and the key to learning visual representations. Inspired by the observation that CNN-learned features are naturally decoupled with the norm of featur
Externí odkaz:
http://arxiv.org/abs/1804.08071
We propose a robust elastic net (REN) model for high-dimensional sparse regression and give its performance guarantees (both the statistical error bound and the optimization bound). A simple idea of trimming the inner product is applied to the elasti
Externí odkaz:
http://arxiv.org/abs/1511.04690