Results 21 to 30 of about 31,762 (259)
A Survey of Weakly-supervised Image Semantic Segmentation Based on Image-level Labels
Taiyuan Ligong Daxue xuebao, 2021 According to the different ways of image-level label location inference, the weakly-supervised image semantic segmentation methods with image-level labels were divided into superpixel-based methods and classification-network-prior based methods.
Xinlin XIE +5 more
doaj +1 more source
Phenotypic Analysis of Diseased Plant Leaves Using Supervised and Weakly Supervised Deep Learning
Plant Phenomics, 2023 Deep learning and computer vision have become emerging tools for diseased plant phenotyping. Most previous studies focused on image-level disease classification.
Lei Zhou +4 more
doaj +1 more source
Deep Weakly Supervised Positioning
CoRR, 2021 8 pages, 8 figures, submitted to IEEE Robotics and Automation Letters (RA-L) and 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021)
Ruoyu Wang 0012 +4 more
openaire +2 more sources
Sensors, 2021 Gas-path anomalies account for more than 90% of all civil aero-engine anomalies. It is essential to develop accurate gas-path anomaly detection methods.
Hao Sun, Xuyun Fu, Shisheng Zhong
doaj +1 more source
OVERVIEW OF COMPUTER VISION SUPERVISED LEARNING TECHNIQUES FOR LOW-DATA TRAINING [PDF]
Journal of Engineering Science (Chişinău), 2020 In the age of big data and machine learning the costs to turn the data into fuel for the algorithms is prohibitively high. Organizations that can train better models with fewer annotation efforts will have a competitive edge.
BURLACU, Alexandru
doaj +1 more source
Weakly supervised parsing with rules [PDF]
Interspeech 2013, 2013 This work proposes a new research direction to address the lack of structures in traditional n-gram models. It is based on a weakly supervised dependency parser that can model speech syntax without relying on any annotated training corpus. La- beled data is replaced by a few hand-crafted rules that encode basic syntactic knowledge.
Christophe Cerisara +2 more
openaire +1 more source
Safe Weakly Supervised Learning [PDF]
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 2021 Weakly supervised learning (WSL) refers to learning from a large amount of weak supervision data. This includes i) incomplete supervision (e.g., semi-supervised learning); ii) inexact supervision (e.g., multi-instance learning) and iii) inaccurate supervision (e.g., label noise learning). Unlike supervised learning which typically achieves performance
openaire +1 more source
Agriculture, 2020 Rice is one of the most important staple food sources worldwide. Effective and cheap monitoring of rice planting areas is demanded by many developing countries.
Mo Wang, Jing Wang, Li Chen
doaj +1 more source
You can simply rely on communities for a robust characterization of stances
Proceedings of the International Florida Artificial Intelligence Research Society Conference, 2021 We show that the structure of communities in social me- dia provides robust information for weakly supervised approaches to assign stances to tweets.
Damián Ariel Furman +4 more
doaj +1 more source
Salvage of Supervision in Weakly Supervised Object Detection
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022 Weakly supervised object detection~(WSOD) has recently attracted much attention. However, the lack of bounding-box supervision makes its accuracy much lower than fully supervised object detection (FSOD), and currently modern FSOD techniques cannot be applied to WSOD.
Lin Sui, Chen-Lin Zhang, Jianxin Wu 0001
openaire +4 more sources