Results 11 to 20 of about 2,514,522 (357)
Want To Reduce Labeling Cost? GPT-3 Can Help [PDF]
Conference on Empirical Methods in Natural Language Processing, 2021 Data annotation is a time-consuming and labor-intensive process for many NLP tasks. Although there exist various methods to produce pseudo data labels, they are often task-specific and require a decent amount of labeled data to start with.
Shuohang Wang +4 more
semanticscholar +1 more source
CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT [PDF]
Conference on Empirical Methods in Natural Language Processing, 2020 The extraction of labels from radiology text reports enables large-scale training of medical imaging models. Existing approaches to report labeling typically rely either on sophisticated feature engineering based on medical domain knowledge or manual ...
Akshay Smit +5 more
semanticscholar +1 more source
SPICE: Semantic Pseudo-Labeling for Image Clustering [PDF]
IEEE Transactions on Image Processing, 2021 The similarity among samples and the discrepancy among clusters are two crucial aspects of image clustering. However, current deep clustering methods suffer from inaccurate estimation of either feature similarity or semantic discrepancy.
Chuang Niu, Hongming Shan, Ge Wang
semanticscholar +1 more source
End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF [PDF]
Annual Meeting of the Association for Computational Linguistics, 2016 State-of-the-art sequence labeling systems traditionally require large amounts of task-specific knowledge in the form of hand-crafted features and data pre-processing.
Xuezhe Ma, E. Hovy
semanticscholar +1 more source
Deciphering molecular interactions by proximity labeling
Nature Methods, 2021 Many biological processes are executed and regulated through the molecular interactions of proteins and nucleic acids. Proximity labeling (PL) is a technology for tagging the endogenous interaction partners of specific protein ‘baits’, via genetic fusion
W. Qin +3 more
semanticscholar +1 more source
Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning [PDF]
IEEE International Joint Conference on Neural Network, 2019 Semi-supervised learning, i.e. jointly learning from labeled and unlabeled samples, is an active research topic due to its key role on relaxing human supervision. In the context of image classification, recent advances to learn from unlabeled samples are
Eric Arazo +4 more
semanticscholar +1 more source
Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels [PDF]
Computer Vision and Pattern Recognition, 2021 ImageNet has been the most popular image classification benchmark, but it is also the one with a significant level of label noise. Recent studies have shown that many samples contain multiple classes, despite being assumed to be a single-label benchmark.
Sangdoo Yun +5 more
semanticscholar +1 more source
Edge-Labeling Graph Neural Network for Few-Shot Learning [PDF]
Computer Vision and Pattern Recognition, 2019 In this paper, we propose a novel edge-labeling graph neural network (EGNN), which adapts a deep neural network on the edge-labeling graph, for few-shot learning.
Jongmin Kim +3 more
semanticscholar +1 more source
Vertex Graceful Labeling-Some Path Related Graphs [PDF]
, 2013 Treating subjects as vertex graceful graphs, vertex graceful labeling, caterpillar, actinia graphs, Smarandachely vertex m ...
Balaganesan, P. +2 more
core +1 more source
Annals of Mathematics and Artificial Intelligence, 2008 zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Arnaud Fietzke, Christoph Weidenbach
openaire +1 more source