Results 21 to 30 of about 12,455,841 (338)
Active Learning for Deep Object Detection via Probabilistic Modeling [PDF]
IEEE International Conference on Computer Vision, 2021 Active learning aims to reduce labeling costs by selecting only the most informative samples on a dataset. Few existing works have addressed active learning for object detection.
Jiwoong Choi +4 more
semanticscholar +1 more source
Active learning strategies for an effective mathematics teaching and learning
European Journal of Science and Mathematics Education, 2023 Learning is an active enterprise, where three dimensions stand out, cognitive, social, and physical, and, in addition, not all students learn in the same way.
Isabel Vale, Ana Barbosa
semanticscholar +1 more source
A Framework and Benchmark for Deep Batch Active Learning for Regression [PDF]
Journal of machine learning research, 2022 The acquisition of labels for supervised learning can be expensive. To improve the sample efficiency of neural network regression, we study active learning methods that adaptively select batches of unlabeled data for labeling.
David Holzmüller +3 more
semanticscholar +1 more source
Influence Selection for Active Learning [PDF]
IEEE International Conference on Computer Vision, 2021 The existing active learning methods select the samples by evaluating the sample’s uncertainty or its effect on the diversity of labeled datasets based on different task-specific or model-specific criteria.
Zhuoming Liu +5 more
semanticscholar +1 more source
Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering [PDF]
Annual Meeting of the Association for Computational Linguistics, 2021 Active learning promises to alleviate the massive data needs of supervised machine learning: it has successfully improved sample efficiency by an order of magnitude on traditional tasks like topic classification and object recognition.
Siddharth Karamcheti +3 more
semanticscholar +1 more source
The Curious Construct of Active Learning
Psychological Science in the Public Interest, 2021 The construct of active learning permeates undergraduate education in science, technology, engineering, and mathematics (STEM), but despite its prevalence, the construct means different things to different people, groups, and STEM domains.
D. Lombardi, T. Shipley
semanticscholar +1 more source
Active Learning for Deep Visual Tracking [PDF]
IEEE Transactions on Neural Networks and Learning Systems, 2021 Convolutional neural networks (CNNs) have been successfully applied to the single target tracking task in recent years. Generally, training a deep CNN model requires numerous labeled training samples, and the number and quality of these samples directly ...
Di Yuan +4 more
semanticscholar +1 more source
The MLIP package: moment tensor potentials with MPI and active learning [PDF]
Machine Learning: Science and Technology, 2020 The subject of this paper is the technology (the ‘how’) of constructing machine-learning interatomic potentials, rather than science (the ‘what’ and ‘why’) of atomistic simulations using machine-learning potentials. Namely, we illustrate how to construct
I. Novikov +3 more
semanticscholar +1 more source
Semi-Supervised Active Learning with Temporal Output Discrepancy [PDF]
IEEE International Conference on Computer Vision, 2021 While deep learning succeeds in a wide range of tasks, it highly depends on the massive collection of annotated data which is expensive and time-consuming.
Siyu Huang +4 more
semanticscholar +1 more source
Learning Loss for Active Learning [PDF]
Computer Vision and Pattern Recognition, 2019 The performance of deep neural networks improves with more annotated data. The problem is that the budget for annotation is limited. One solution to this is active learning, where a model asks human to annotate data that it perceived as uncertain.
Donggeun Yoo, In-So Kweon
semanticscholar +1 more source