Improving ranking-based question answering with weak supervision for low-resource Qur’anic texts
Sign Up to like & getrecommendations! Published in 2024 at "Artificial Intelligence Review"
DOI: 10.1007/s10462-024-10964-3
Abstract: This work tackles the challenge of ranking-based machine reading comprehension (MRC), where a question answering (QA) system generates a ranked list of relevant answers for each question instead of simply extracting a single answer. We… read more here.
Keywords: ranking based; resource; weak supervision; question answering ... See more keywords
Robust Foot Motion Recognition Using Stride Detection and Weak Supervision-Based Fast Labeling
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Sensors Journal"
DOI: 10.1109/jsen.2021.3075151
Abstract: Foot motion recognition in daily life faces two challenges imposed by traditional machine learning frameworks: how to robustly recognize various foot motions from continuous movements in uncontrolled environments, and how to accurately extract ground truths.… read more here.
Keywords: foot motions; stride detection; foot; weak supervision ... See more keywords
Mixture to Mixture: Leveraging Close-Talk Mixtures as Weak-Supervision for Speech Separation
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Signal Processing Letters"
DOI: 10.1109/lsp.2024.3417284
Abstract: We propose mixture to mixture (M2M) training, a weakly-supervised neural speech separation algorithm that leverages close-talk mixtures as a weak supervision for training discriminative models to separate far-field mixtures. Our idea is that, for a… read more here.
Keywords: close talk; weak supervision; separation; mixture ... See more keywords
Constrained Deep Weak Supervision for Histopathology Image Segmentation
Sign Up to like & getrecommendations! Published in 2017 at "IEEE Transactions on Medical Imaging"
DOI: 10.1109/tmi.2017.2724070
Abstract: In this paper, we develop a new weakly supervised learning algorithm to learn to segment cancerous regions in histopathology images. This paper is under a multiple instance learning (MIL) framework with a new formulation, deep… read more here.
Keywords: image; weak supervision; histopathology; histopathology image ... See more keywords
Disentangling Normal Aging from Severity of Disease via Weak Supervision on Longitudinal MRI.
Sign Up to like & getrecommendations! Published in 2022 at "IEEE transactions on medical imaging"
DOI: 10.1109/tmi.2022.3166131
Abstract: The continuous progression of neurological diseases are often categorized into conditions according to their severity. To relate the severity to changes in brain morphometry, there is a growing interest in replacing these categories with a… read more here.
Keywords: via weak; weak supervision; aging severity; disease ... See more keywords
Learning to Detect Salient Object with Multi-source Weak Supervision.
Sign Up to like & getrecommendations! Published in 2021 at "IEEE transactions on pattern analysis and machine intelligence"
DOI: 10.1109/tpami.2021.3059783
Abstract: High-cost pixel-level annotations makes it appealing to train saliency detection models with weak supervision. However, a single weak supervision source hardly contain enough information to train a well-performing model. To this end, we introduce a… read more here.
Keywords: salient object; weak supervision; supervision; source ... See more keywords
Weak supervision, strong results: Automating melanocyte lesion diagnosis with deep learning
Sign Up to like & getrecommendations! Published in 2024 at "Journal of the European Academy of Dermatology and Venereology"
DOI: 10.1111/jdv.20382
Abstract: a significant study exploring the application of weakly supervised deep learning (DL) models— Trans-MIL, CLAM and DTFD-MIL—for distinguishing melanomas from naevi on haematoxylin and eosin (H&E)- stained pathology slides. Achieving remarkable read more here.
Keywords: deep learning; supervision strong; learning; results automating ... See more keywords
Spatio-Frequency Decoupled Weak-Supervision for Face Reconstruction
Sign Up to like & getrecommendations! Published in 2022 at "Computational Intelligence and Neuroscience"
DOI: 10.1155/2022/5903514
Abstract: 3D face reconstruction has witnessed considerable progress in recovering 3D face shapes and textures from in-the-wild images. However, due to a lack of texture detail information, the reconstructed shape and texture based on deep learning… read more here.
Keywords: frequency; reconstruction; weak supervision; face reconstruction ... See more keywords
Rule-Enhanced Active Learning for Semi-Automated Weak Supervision
Sign Up to like & getrecommendations! Published in 2022 at "Artificial intelligence"
DOI: 10.3390/ai3010013
Abstract: A major bottleneck preventing the extension of deep learning systems to new domains is the prohibitive cost of acquiring sufficient training labels. Alternatives such as weak supervision, active learning, and fine-tuning of pretrained models reduce… read more here.
Keywords: active learning; weak supervision; supervision; labeling functions ... See more keywords
Collecting a Large Scale Dataset for Classifying Fake News Tweets Using Weak Supervision
Sign Up to like & getrecommendations! Published in 2021 at "Future Internet"
DOI: 10.3390/fi13050114
Abstract: The problem of automatic detection of fake news in social media, e.g., on Twitter, has recently drawn some attention. Although, from a technical perspective, it can be regarded as a straight-forward, binary classification problem, the… read more here.
Keywords: large scale; classification; weak supervision; dataset ... See more keywords