paper-with-me

홈 › Papers

Bidirectional Domain Adaptation Using Weighted Multi-Task Learning

2021-08-01 · ACL (IWPT) 2021 8 · Daniel Dakota, Zeeshan Ali Sayyed, Sandra Kübler

Domain adaption in syntactic parsing is still a significant challenge. We address the issue of data imbalance between the in-domain and out-of-domain treebank typically used for the problem. We define domain adaptation as a Multi-task learning (MTL) problem, which allows us to train two parsers, one for each do-main. Our results show that the MTL approach is beneficial for the smaller treebank. For the larger treebank, we need to use loss weighting in order to avoid a decrease in performance be-low the single task. In order to determine towhat degree the data imbalance between two domains and the domain differences affect results, we also carry out an experiment with two imbalanced in-domain treebanks and show that loss weighting also improves performance in an in-domain setting. Given loss weighting in MTL, we can improve results for both parsers.

📄 PDF Abstract BibTeX

Code (1)

zeeshansayyed/multiparser 공식 구현 pytorch

Tasks

Domain AdaptationMulti-Task Learning

Similar Papers 제목 키워드 기반

Cross-Modality Brain Tumor Segmentation via Bidirectional Global-to-Local Unsupervised Domain Adaptation

2021-05-17 · Kelei He, Wen Ji, Tao Zhou, Zhuoyuan Li 외

Accurate segmentation of brain tumors from multi-modal Magnetic Resonance (MR) images is essential in brain tumor diagnosis and treatment. However, due to the existence of domain shifts among different modalities, the pe…

Brain Tumor SegmentationDomain AdaptationImage GenerationSegmentation+2

Bidirectional Learning for Domain Adaptation of Semantic Segmentation

2019-04-24 · CVPR 2019 6 · Yunsheng Li, Lu Yuan, Nuno Vasconcelos

Domain adaptation for semantic image segmentation is very necessary since manually labeling large datasets with pixel-level labels is expensive and time consuming. Existing domain adaptation techniques either work on lim…

Domain AdaptationImage SegmentationImage-to-Image TranslationSegmentation+4

Domain Adaptation via Bidirectional Cross-Attention Transformer

2022-01-15 · Xiyu Wang, Pengxin Guo, Yu Zhang

Domain Adaptation (DA) aims to leverage the knowledge learned from a source domain with ample labeled data to a target domain with unlabeled data only. Most existing studies on DA contribute to learning domain-invariant …

Domain Adaptation

Unsupervised Bidirectional Cross-Modality Adaptation via Deeply Synergistic Image and Feature Alignment for Medical Image Segmentation

2020-02-06 · Cheng Chen, Qi Dou, Hao Chen, Jing Qin 외

Unsupervised domain adaptation has increasingly gained interest in medical image computing, aiming to tackle the performance degradation of deep neural networks when being deployed to unseen data with heterogeneous chara…

Domain AdaptationImage SegmentationMedical Image SegmentationOrgan Segmentation+3

Bidirectional Domain Mixup for Domain Adaptive Semantic Segmentation

2023-03-17 · Daehan Kim, Minseok Seo, KwanYong Park, Inkyu Shin 외

Mixup provides interpolated training samples and allows the model to obtain smoother decision boundaries for better generalization. The idea can be naturally applied to the domain adaptation task, where we can mix the so…

Domain AdaptationPseudo LabelSemantic Segmentation