Results 11 to 20 of about 16,769 (297)

Weakly Supervised Causal Representation Learning [PDF]

Advances in Neural Information Processing Systems 35, 2022
Learning high-level causal representations together with a causal model from unstructured low-level data such as pixels is impossible from observational data alone. We prove under mild assumptions that this representation is however identifiable in a weakly supervised setting. This involves a dataset with paired samples before and after random, unknown
Johann Brehmer, Pim de Haan, Phillip Lippe, Taco Cohen   +3 more
openaire   +6 more sources

Defect detection using weakly supervised learning [PDF]

2023 IEEE International Conference on Imaging Systems and Techniques (IST), 2023
In many real-world scenarios, obtaining large amounts of labeled data can be a daunting task. Weakly supervised learning techniques have gained significant attention in recent years as an alternative to traditional supervised learning, as they enable training models using only a limited amount of labeled data. In this paper, the performance of a weakly
Sevetlidis, Vasileios, Pavlidis, George, Balaska, Vassiliki, Psomoulis, Athanasios, Mouroutsos, Spyridon, Gasteratos, Antonios   +5 more
openaire   +3 more sources

Weakly Supervised Learning of Objects, Attributes and Their Associations [PDF]

, 2014
14 pages, Accepted to ECCV ...
Shi, Z, Yang, Y, Hospedales, TM, Xiang, T   +3 more
openaire   +4 more sources

Weakly-Supervised Learning of Visual Relations [PDF]

2017 IEEE International Conference on Computer Vision (ICCV), 2017
This paper introduces a novel approach for modeling visual relations between pairs of objects. We call relation a triplet of the form (subject, predicate, object) where the predicate is typically a preposition (eg. 'under', 'in front of') or a verb ('hold', 'ride') that links a pair of objects (subject, object).
Julia Peyre, Ivan Laptev, Cordelia Schmid, Josef Sivic   +3 more
openaire   +6 more sources

Weakly supervised classification in high energy physics [PDF]

Journal of High Energy Physics, 2017
As machine learning algorithms become increasingly sophisticated to exploit subtle features of the data, they often become more dependent on simulations.
Lucio Mwinmaarong Dery, Benjamin Nachman, Francesco Rubbo, Ariel Schwartzman   +3 more
doaj   +3 more sources

Reducing Label Dependency in Human Activity Recognition with Wearables: From Supervised Learning to Novel Weakly Self-Supervised Approaches [PDF]

Sensors
Human activity recognition (HAR) using wearable sensors has advanced through various machine learning paradigms, each with inherent trade-offs between performance and labeling requirements.
Taoran Sheng, Manfred Huber
doaj   +2 more sources

Weakly Supervised Contrastive Learning [PDF]

2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021
Unsupervised visual representation learning has gained much attention from the computer vision community because of the recent achievement of contrastive learning. Most of the existing contrastive learning frameworks adopt the instance discrimination as the pretext task, which treating every single instance as a different class.
Mingkai Zheng, Fei Wang 0032, Shan You, Chen Qian 0006, Changshui Zhang, Xiaogang Wang 0001, Chang Xu 0002   +6 more
openaire   +2 more sources

Infrared Ship Segmentation Based on Weakly-Supervised and Semi-Supervised Learning [PDF]

IEEE Access
Existing fully-supervised semantic segmentation methods have achieved good performance. However, they all rely on high-quality pixel-level labels. To minimize the annotation costs, weakly-supervised methods or semi-supervised methods are proposed.
Isa Ali Ibrahim, Abdallah Namoun, Sami Ullah, Hisham Alasmary, Muhammad Waqas, Iftekhar Ahmad   +5 more
doaj   +3 more sources

Weakly Supervised Correspondence Learning

2022 International Conference on Robotics and Automation (ICRA), 2022
Correspondence learning is a fundamental problem in robotics, which aims to learn a mapping between state, action pairs of agents of different dynamics or embodiments. However, current correspondence learning methods either leverage strictly paired data -- which are often difficult to collect -- or learn in an unsupervised fashion from unpaired data ...
Zihan Wang, Zhangjie Cao, Yilun Hao, Dorsa Sadigh   +3 more
openaire   +2 more sources

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