Learning with Weak Supervision from Physics and Data-Driven Constraints
نویسندگان
چکیده
منابع مشابه
Learning to Learn from Weak Supervision by Full Supervision
In this paper, we propose a method for training neural networks when we have a large set of data with weak labels and a small amount of data with true labels. In our proposed model, we train two neural networks: a target network, the learner and a confidence network, the meta-learner. The target network is optimized to perform a given task and is trained using a large set of unlabeled data that...
متن کاملLearning Transformation Invariant Representations with Weak Supervision
Benjamin Coors1,2, Alexandru Condurache2, Alfred Mertins3 and Andreas Geiger1,4 1Autonomous Vision Group, MPI for Intelligent Systems, Tübingen, Germany 2Robert Bosch GmbH, Leonberg, Germany 3Institute for Signal Processing, University of Lübeck, Germany 4Computer Vision and Geometry Group, ETH Zürich, Switzerland {benjamin.coors,andreas.geiger}@tue.mpg.de, [email protected], m...
متن کاملLearning under Distributed Weak Supervision
The availability of training data for supervision is a frequently encountered bottleneck of medical image analysis methods. While typically established by a clinical expert rater, the increase in acquired imaging data renders traditional pixel-wise segmentations less feasible. In this paper, we examine the use of a crowdsourcing platform for the distribution of super-pixel weak annotation tasks...
متن کاملEnhancing Learning from Imbalanced Classes via Data Preprocessing: A Data-Driven Application in Metabolomics Data Mining
This paper presents a data mining application in metabolomics. It aims at building an enhanced machine learning classifier that can be used for diagnosing cachexia syndrome and identifying its involved biomarkers. To achieve this goal, a data-driven analysis is carried out using a public dataset consisting of 1H-NMR metabolite profile. This dataset suffers from the problem of imbalanced classes...
متن کاملSupplementary Material for Learning 3D Shape Completion from Laser Scan Data with Weak Supervision
This document provides additional details regarding the used datasets and further experimental results complementary to the main paper. In Section 2, we discuss technical details regarding the introduced, synthetic datasets derived from ShapeNet [2], referred to as SN-clean and SN-noisy, the synthetic dataset derived from ModelNet [17], as well as the dataset extracted from KITTI [9]. Then, in ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: AI Magazine
سال: 2018
ISSN: 2371-9621,0738-4602
DOI: 10.1609/aimag.v39i1.2776