paper-with-me

홈 › Papers

Transductive Auxiliary Task Self-Training for Neural Multi-Task Models

2019-08-16 · WS 2019 11 · Johannes Bjerva, Katharina Kann, Isabelle Augenstein

Multi-task learning and self-training are two common ways to improve a machine learning model's performance in settings with limited training data. Drawing heavily on ideas from those two approaches, we suggest transductive auxiliary task self-training: training a multi-task model on (i) a combination of main and auxiliary task training data, and (ii) test instances with auxiliary task labels which a single-task version of the model has previously generated. We perform extensive experiments on 86 combinations of languages and tasks. Our results are that, on average, transductive auxiliary task self-training improves absolute accuracy by up to 9.56% over the pure multi-task model for dependency relation tagging and by up to 13.03% for semantic tagging.

📄 PDF Abstract BibTeX arXiv:1908.06136

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Task Learning

Similar Papers 제목 키워드 기반

Semi-Supervised SAR ATR Framework with Transductive Auxiliary Segmentation

2023-08-31 · Chenwei Wang, Xiaoyu Liu, Yulin Huang, Siyi Luo 외

Convolutional neural networks (CNNs) have achieved high performance in synthetic aperture radar (SAR) automatic target recognition (ATR). However, the performance of CNNs depends heavily on a large amount of training dat…

Few-Shot LearningInductive BiasSegmentation

Transductive Multi-view Zero-Shot Learning

2015-01-19 · Yanwei Fu, Timothy M. Hospedales, Tao Xiang, Shaogang Gong

Most existing zero-shot learning approaches exploit transfer learning via an intermediate-level semantic representation shared between an annotated auxiliary dataset and a target dataset with different classes and no ann…

Transfer LearningZero-Shot Learning

Transductive Multi-class and Multi-label Zero-shot Learning

2015-03-26 · Yanwei Fu, Yongxin Yang, Timothy M. Hospedales, Tao Xiang 외

Recently, zero-shot learning (ZSL) has received increasing interest. The key idea underpinning existing ZSL approaches is to exploit knowledge transfer via an intermediate-level semantic representation which is assumed t…

Multi-label zero-shot learningTransductive LearningTransfer LearningZero-Shot Learning

Transductive image segmentation: Self-training and effect of uncertainty estimation

2021-07-19 · Konstantinos Kamnitsas, Stefan Winzeck, Evgenios N. Kornaropoulos, Daniel Whitehouse 외

Semi-supervised learning (SSL) uses unlabeled data during training to learn better models. Previous studies on SSL for medical image segmentation focused mostly on improving model generalization to unseen data. In some a…

Image SegmentationMedical Image AnalysisMedical Image SegmentationSegmentation+2

Composite Learning for Robust and Effective Dense Predictions

2022-10-13 · Menelaos Kanakis, Thomas E. Huang, David Bruggemann, Fisher Yu 외

Multi-task learning promises better model generalization on a target task by jointly optimizing it with an auxiliary task. However, the current practice requires additional labeling efforts for the auxiliary task, while …

Boundary DetectionDepth EstimationMonocular Depth EstimationMulti-Task Learning+2