English
Related papers

Related papers: Maximum Batch Frobenius Norm for Multi-Domain Text…

200 papers

Multi-domain text classification (MDTC) endeavors to harness available resources from correlated domains to enhance the classification accuracy of the target domain. Presently, most MDTC approaches that embrace adversarial training and the…

Computation and Language · Computer Science 2024-03-05 Yuan Wu

The learning of the deep networks largely relies on the data with human-annotated labels. In some label insufficient situations, the performance degrades on the decision boundary with high data density. A common solution is to directly…

Computer Vision and Pattern Recognition · Computer Science 2020-03-30 Shuhao Cui , Shuhui Wang , Junbao Zhuo , Liang Li , Qingming Huang , Qi Tian

In this paper we propose a novel dual adversarial co-learning approach for multi-domain text classification (MDTC). The approach learns shared-private networks for feature extraction and deploys dual adversarial regularizations to align…

Machine Learning · Computer Science 2019-09-19 Yuan Wu , Yuhong Guo

Many text classification tasks are known to be highly domain-dependent. Unfortunately, the availability of training data can vary drastically across domains. Worse still, for some domains there may not be any annotated data at all. In this…

Computation and Language · Computer Science 2018-02-16 Xilun Chen , Claire Cardie

Due to the domain discrepancy in visual domain adaptation, the performance of source model degrades when bumping into the high data density near decision boundary in target domain. A common solution is to minimize the Shannon Entropy to…

Computer Vision and Pattern Recognition · Computer Science 2021-08-05 Shuhao Cui , Shuhui Wang , Junbao Zhuo , Liang Li , Qingming Huang , Qi Tian

In recent years, pattern analysis plays an important role in data mining and recognition, and many variants have been proposed to handle complicated scenarios. In the literature, it has been quite familiar with high dimensionality of data…

Machine Learning · Computer Science 2018-11-09 Miao Cheng , Zunren Liu , Hongwei Zou , Ah Chung Tsoi

The most successful multi-domain text classification (MDTC) approaches employ the shared-private paradigm to facilitate the enhancement of domain-invariant features through domain-specific attributes. Additionally, they employ adversarial…

Computation and Language · Computer Science 2023-12-20 Juntao Hu , Yuan Wu

Feature selection is an important pre-processing step for many pattern classification tasks. Traditionally, feature selection methods are designed to obtain a feature subset that can lead to high classification accuracy. However,…

Machine Learning · Computer Science 2012-05-03 Rui Wang , Ke Tang

Although achieving remarkable progress, it is very difficult to induce a supervised classifier without any labeled data. Unsupervised domain adaptation is able to overcome this challenge by transferring knowledge from a labeled source…

Machine Learning · Computer Science 2021-06-29 Yuntao Du , Ruiting Zhang , Xiaowen Zhang , Yirong Yao , Hengyang Lu , Chongjun Wang

Adversarial training based on the maximum classifier discrepancy between two classifier structures has achieved great success in unsupervised domain adaptation tasks for image classification. The approach adopts the structure of two…

Computer Vision and Pattern Recognition · Computer Science 2022-04-19 Yiju Yang , Taejoon Kim , Guanghui Wang

Maximum entropy approach to classification is very well studied in applied statistics and machine learning and almost all the methods that exists in literature are discriminative in nature. In this paper, we introduce a maximum entropy…

Information Theory · Computer Science 2013-12-31 Ambedkar Dukkipati , Gaurav Pandey , Debarghya Ghoshdastidar , Paramita Koley , D. M. V. Satya Sriram

Multi-domain text classification can automatically classify texts in various scenarios. Due to the diversity of human languages, texts with the same label in different domains may differ greatly, which brings challenges to the multi-domain…

Computation and Language · Computer Science 2022-04-27 Xuefeng Li , Hao Lei , Liwen Wang , Guanting Dong , Jinzheng Zhao , Jiachi Liu , Weiran Xu , Chunyun Zhang

In the era of large language models generating high quality texts, it is a necessity to develop methods for detection of machine-generated text to avoid harmful use or simply due to annotation purposes. It is, however, also important to…

Computation and Language · Computer Science 2024-12-18 Michal Spiegel , Dominik Macko

Using the shared-private paradigm and adversarial training has significantly improved the performances of multi-domain text classification (MDTC) models. However, there are two issues for the existing methods. First, instances from the…

Computation and Language · Computer Science 2021-02-02 Yuan Wu , Diana Inkpen , Ahmed El-Roby

Adversarial attacks induce misclassification by introducing subtle perturbations. Recently, diffusion models are applied to the image classifiers to improve adversarial robustness through adversarial training or by purifying adversarial…

Computer Vision and Pattern Recognition · Computer Science 2024-05-21 Yujie Li , Yanbin Wang , Haitao Xu , Bin Liu , Jianguo Sun , Zhenhao Guo , Wenrui Ma

We present a novel framework that can combine multi-domain learning (MDL), data imputation (DI) and multi-task learning (MTL) to improve performance for classification and regression tasks in different domains. The core of our method is an…

Machine Learning · Computer Science 2020-03-18 Andre Mendes , Julian Togelius , Leandro dos Santos Coelho

Federated learning enables multiple medical institutions to train a global model without sharing data, yet feature heterogeneity from diverse scanners or protocols remains a major challenge. Many existing works attempt to address this issue…

Computer Vision and Pattern Recognition · Computer Science 2026-01-23 Xingyue Zhao , Wenke Huang , Xingguang Wang , Haoyu Zhao , Linghao Zhuang , Anwen Jiang , Guancheng Wan , Mang Ye

Automated feature selection is important for text categorization to reduce the feature size and to speed up the learning process of classifiers. In this paper, we present a novel and efficient feature selection framework based on the…

Machine Learning · Statistics 2016-11-15 Bo Tang , Steven Kay , Haibo He

Existing domain adaptation methods aim to reduce the distributional difference between the source and target domains and respect their specific discriminative information, by establishing the Maximum Mean Discrepancy (MMD) and the…

Machine Learning · Computer Science 2020-07-03 Wei Wang , Haojie Li , Zhengming Ding , Zhihui Wang

Deep neural networks often degrade significantly when training data suffer from class imbalance problems. Existing approaches, e.g., re-sampling and re-weighting, commonly address this issue by rearranging the label distribution of training…

Computer Vision and Pattern Recognition · Computer Science 2020-08-11 Renzhen Wang , Kaiqin Hu , Yanwen Zhu , Jun Shu , Qian Zhao , Deyu Meng
‹ Prev 1 2 3 10 Next ›