Learning safe multi-label prediction for weakly labeled data
Sign Up to like & getrecommendations! Published in 2017 at "Machine Learning"
DOI: 10.1007/s10994-017-5675-z
Abstract: In this paper we study multi-label learning with weakly labeled data, i.e., labels of training examples are incomplete, which commonly occurs in real applications, e.g., image classification, document categorization. This setting includes, e.g., (i) semi-supervised… read more here.
Keywords: label; weakly labeled; multi label; label learning ... See more keywords
SyMIL: MinMax Latent SVM for Weakly Labeled Data
Sign Up to like & getrecommendations! Published in 2018 at "IEEE Transactions on Neural Networks and Learning Systems"
DOI: 10.1109/tnnls.2018.2820055
Abstract: Designing powerful models able to handle weakly labeled data are a crucial problem in machine learning. In this paper, we propose a new multiple instance learning (MIL) framework. Examples are represented as bags of instances,… read more here.
Keywords: standard mil; weakly labeled; latent svm; symil minmax ... See more keywords
SPFTN: A Joint Learning Framework for Localizing and Segmenting Objects in Weakly Labeled Videos
Sign Up to like & getrecommendations! Published in 2020 at "IEEE Transactions on Pattern Analysis and Machine Intelligence"
DOI: 10.1109/tpami.2018.2881114
Abstract: Object localization and segmentation in weakly labeled videos are two interesting yet challenging tasks. Models built for simultaneous object localization and segmentation have been explored in the conventional fully supervised learning scenario to boost the… read more here.
Keywords: learning framework; learning; object localization; localization segmentation ... See more keywords
Multilabel Appliance Classification With Weakly Labeled Data for Non-Intrusive Load Monitoring
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Smart Grid"
DOI: 10.1109/tsg.2022.3191908
Abstract: Non-Intrusive Load Monitoring consists in estimating the power consumption or the states of the appliances using electrical parameters acquired from a single metering point. State-of-the-art approaches are based on deep neural networks, and for training,… read more here.
Keywords: intrusive load; appliance classification; labeled data; weakly labeled ... See more keywords
Counting Activities Using Weakly Labeled Raw Acceleration Data: A Variable-Length Sequence Approach with Deep Learning to Maintain Event Duration Flexibility
Sign Up to like & getrecommendations! Published in 2023 at "Sensors"
DOI: 10.3390/s23115057
Abstract: This paper presents a novel approach for counting hand-performed activities using deep learning and inertial measurement units (IMUs). The particular challenge in this task is finding the correct window size for capturing activities with different… read more here.
Keywords: variable length; deep learning; weakly labeled; approach ... See more keywords