Results 41 to 50 of about 16,769 (297)
Weakly-Supervised Bayesian Learning of a CCG Supertagger [PDF]
, 2018 We present a Bayesian formulation for weakly-supervised learning of a Combinatory Categorial Grammar (CCG) supertagger with an HMM. We assume supervision in the form of a tag dictionary, and our prior encourages the use of crosslinguistically common ...
Noah A. Smith (663492) +3 more
core +1 more source
Instance-Level Contrastive Learning for Weakly Supervised Object Detection
Sensors, 2022 Weakly supervised object detection (WSOD) has received increasing attention in object detection field, because it only requires image-level annotations to indicate the presence or absence of target objects, which greatly reduces the labeling costs ...
Ming Zhang, Bing Zeng
doaj +1 more source
Weakly Supervised Learning for Textbook Question Answering [PDF]
IEEE Transactions on Image Processing, 2021 Textbook Question Answering (TQA) is the task of answering diagram and non-diagram questions given large multi-modal contexts consisting of abundant text and diagrams. Deep text understandings and effective learning of diagram semantics are important for this task due to its specificity. In this paper, we propose a Weakly Supervised learning method for
Jie Ma 0001 +5 more
openaire +2 more sources
Knodle: Modular Weakly Supervised Learning with PyTorch [PDF]
Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021), 2021 Strategies for improving the training and prediction quality of weakly supervised machine learning models vary in how much they are tailored to a specific task or integrated with a specific model architecture. In this work, we introduce Knodle, a software framework that treats weak data annotations, deep learning models, and methods for improving ...
Sedova, Anastasiia +3 more
openaire +2 more sources
Several Studies of Weakly Supervised Learning in Text Classification [PDF]
, 2022 Text classification is one of the most fundamental tasks in Natural Language Processing. How to effectually utilize the unlabeled dataset in text classification and apply weakly supervised learning methods to further improve the performance based on the ...
Luo, Tianyi
core
Remote Sensing, 2020 The lack of pixel-level labeling limits the practicality of deep learning-based building semantic segmentation. Weakly supervised semantic segmentation based on image-level labeling results in incomplete object regions and missing boundary information ...
Jie Chen +4 more
doaj +1 more source
Weakly Supervised Action Selection Learning in Video [PDF]
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021 Localizing actions in video is a core task in computer vision. The weakly supervised temporal localization problem investigates whether this task can be adequately solved with only video-level labels, significantly reducing the amount of expensive and error-prone annotation that is required.
Junwei Ma +3 more
openaire +2 more sources
Unsupervised learning of generative topic saliency for person re-identification [PDF]
, 2014 (c) 2014. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.© 2014. The copyright of this document resides with its authors.
Wang, H +5 more
core +1 more source
Local Feature Discriminant Projection [PDF]
, 2016 In this paper, we propose a novel subspace learning algorithm called Local Feature Discriminant Projection (LFDP) for supervised dimensionality reduction of local features.
Zhen, Xiantong +3 more
core +1 more source
Weakly Supervised Representation Learning with Sparse Perturbations
Advances in Neural Information Processing Systems 35, 2022 The theory of representation learning aims to build methods that provably invert the data generating process with minimal domain knowledge or any source of supervision. Most prior approaches require strong distributional assumptions on the latent variables and weak supervision (auxiliary information such as timestamps) to provide provable ...
Ahuja, Kartik +2 more
openaire +5 more sources