English
Related papers

Related papers: Learning to Contextually Aggregate Multi-Source Su…

200 papers

Crowdsourcing platforms are often used to collect datasets for training machine learning models, despite higher levels of inaccurate labeling compared to expert labeling. There are two common strategies to manage the impact of such noise.…

Computation and Language · Computer Science 2022-06-14 Derek Chen , Zhou Yu , Samuel R. Bowman

Deep learning has produced state-of-the-art results for a variety of tasks. While such approaches for supervised learning have performed well, they assume that training and testing data are drawn from the same distribution, which may not…

Machine Learning · Computer Science 2020-02-10 Garrett Wilson , Diane J. Cook

Representation learning approaches require a massive amount of discriminative training data, which is unavailable in many scenarios, such as healthcare, smart city, education, etc. In practice, people refer to crowdsourcing to get annotated…

Machine Learning · Computer Science 2021-12-17 Yang Hao , Wenbiao Ding , Zitao Liu

Person re-identification (re-ID), is a challenging task due to the high variance within identity samples and imaging conditions. Although recent advances in deep learning have achieved remarkable accuracy in settled scenes, i.e., source…

Computer Vision and Pattern Recognition · Computer Science 2019-12-04 Fengxiang Yang , Ke Li , Zhun Zhong , Zhiming Luo , Xing Sun , Hao Cheng , Xiaowei Guo , Feiyue Huang , Rongrong Ji , Shaozi Li

Majority voting and averaging are common approaches employed to resolve annotator disagreements and derive single ground truth labels from multiple annotations. However, annotators may systematically disagree with one another, often…

Computation and Language · Computer Science 2021-10-13 Aida Mostafazadeh Davani , Mark Díaz , Vinodkumar Prabhakaran

Multi-Source cross-lingual transfer learning deals with the transfer of task knowledge from multiple labelled source languages to an unlabeled target language under the language shift. Existing methods typically focus on weighting the…

Computation and Language · Computer Science 2024-03-08 Ling Ge , Chunming Hu , Guanghui Ma , Jihong Liu , Hong Zhang

Reference texts such as encyclopedias and news articles can manifest biased language when objective reporting is substituted by subjective writing. Existing methods to detect bias mostly rely on annotated data to train machine learning…

Computation and Language · Computer Science 2021-12-20 Timo Spinde , David Krieger , Manuel Plank , Bela Gipp

We address the challenging problem of semi-supervised learning in the context of multiple visual interpretations of the world by finding consensus in a graph of neural networks. Each graph node is a scene interpretation layer, while each…

Computer Vision and Pattern Recognition · Computer Science 2020-12-04 Marius Leordeanu , Mihai Pirvu , Dragos Costea , Alina Marcu , Emil Slusanschi , Rahul Sukthankar

Learning robust contextual knowledge from unlabeled videos is essential for advancing self-supervised tracking. However, conventional self-supervised trackers lack effective context modeling, while existing context association methods based…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Yaozong Zheng , Qihua Liang , Bineng Zhong , Shuimu Zeng , Yuanliang Xue , Ning Li , Shuxiang Song

Multi-Label Text Classification (MLTC) is a fundamental task in the field of Natural Language Processing (NLP) that involves the assignment of multiple labels to a given text. MLTC has gained significant importance and has been widely…

Computation and Language · Computer Science 2024-03-20 Bo Li , Yuyan Chen , Liang Zeng

Emotion recognition algorithms rely on data annotated with high quality labels. However, emotion expression and perception are inherently subjective. There is generally not a single annotation that can be unambiguously declared "correct".…

While unsupervised domain adaptation methods based on deep architectures have achieved remarkable success in many computer vision tasks, they rely on a strong assumption, i.e. labeled source data must be available. In this work we overcome…

Computer Vision and Pattern Recognition · Computer Science 2020-08-12 Willi Menapace , Stéphane Lathuilière , Elisa Ricci

Crowdsourced labels play a crucial role in evaluating task-oriented dialogue systems (TDSs). Obtaining high-quality and consistent ground-truth labels from annotators presents challenges. When evaluating a TDS, annotators must fully…

Computation and Language · Computer Science 2024-04-16 Clemencia Siro , Mohammad Aliannejadi , Maarten de Rijke

A popular approach for large scale data annotation tasks is crowdsourcing, wherein each data point is labeled by multiple noisy annotators. We consider the problem of inferring ground truth from noisy ordinal labels obtained from multiple…

Machine Learning · Statistics 2013-05-02 Balaji Lakshminarayanan , Yee Whye Teh

Large-scale datasets are important for the development of deep learning models. Such datasets usually require a heavy workload of annotations, which are extremely time-consuming and expensive. To accelerate the annotation procedure,…

Machine Learning · Computer Science 2024-03-13 Xiaoqian Ruan , Gaoang Wang

Computing universal distributed representations of sentences is a fundamental task in natural language processing. We propose ConsSent, a simple yet surprisingly powerful unsupervised method to learn such representations by enforcing…

Computation and Language · Computer Science 2019-01-25 Siddhartha Brahma

In unsupervised domain adaptation (UDA), a classifier for the target domain is trained with massive true-label data from the source domain and unlabeled data from the target domain. However, collecting fully-true-label data in the source…

Machine Learning · Computer Science 2021-03-05 Yiyang Zhang , Feng Liu , Zhen Fang , Bo Yuan , Guangquan Zhang , Jie Lu

Training NLP systems typically assumes access to annotated data that has a single human label per example. Given imperfect labeling from annotators and inherent ambiguity of language, we hypothesize that single label is not sufficient to…

Computation and Language · Computer Science 2021-09-14 Shujian Zhang , Chengyue Gong , Eunsol Choi

In order to leverage and profit from unlabelled data, semi-supervised frameworks for semantic segmentation based on consistency training have been proven to be powerful tools to significantly improve the performance of purely supervised…

Computer Vision and Pattern Recognition · Computer Science 2021-12-09 Max Coenen , Tobias Schack , Dries Beyer , Christian Heipke , Michael Haist

Training deep networks for semantic segmentation requires annotation of large amounts of data, which can be time-consuming and expensive. Unfortunately, these trained networks still generalize poorly when tested in domains not consistent…

Computer Vision and Pattern Recognition · Computer Science 2018-11-09 Kashyap Chitta , Jianwei Feng , Martial Hebert