Results 21 to 30 of about 16,769 (297)
Learning Uncertainty-Aware Label Transition for Weakly Supervised Solar Panel Mapping with Aerial Images [PDF]
, 2022 Weakly supervised solar panel mapping has shown its advantages in automatically detecting solar panels from remote sensing images with low annotation costs.
Zhou, Jun +3 more
core +1 more source
Weakly supervised learning of allomorphy [PDF]
Proceedings of the First Workshop on Subword and Character Level Models in NLP, 2017 Most NLP resources that offer annotations at the word segment level provide morphological annotation that includes features indicating tense, aspect, modality, gender, case, and other inflectional information. Such information is rarely aligned to the relevant parts of the words—i.e. the allomorphs, as such annotation would be very costly.
Miikka Silfverberg, Mans Hulden
openaire +1 more source
Weakly-Supervised Learning of Human Dynamics [PDF]
, 2020 This paper proposes a weakly-supervised learning framework for dynamics estimation from human motion. Although there are many solutions to capture pure human motion readily available, their data is not sufficient to analyze quality and efficiency of movements.
Petrissa Zell +2 more
openaire +2 more sources
Learning Weakly-Supervised Contrastive Representations
CoRR, 2022 We argue that a form of the valuable information provided by the auxiliary information is its implied data clustering information. For instance, considering hashtags as auxiliary information, we can hypothesize that an Instagram image will be semantically more similar with the same hashtags. With this intuition, we present a two-stage weakly-supervised
Yao-Hung Hubert Tsai +5 more
openaire +3 more sources
Sensors, 2021 Recent advances in deep learning models for image interpretation finally made it possible to automate construction site monitoring processes that rely on remote sensing. However, the major drawback of these models is their dependency on large datasets of
Suzanna Cuypers +2 more
doaj +1 more source
Weakly-supervised deep learning for ultrasound diagnosis of breast cancer
Scientific Reports, 2021 Conventional deep learning (DL) algorithm requires full supervision of annotating the region of interest (ROI) that is laborious and often biased. We aimed to develop a weakly-supervised DL algorithm that diagnosis breast cancer at ultrasound without ...
Jaeil Kim +9 more
doaj +1 more source
Decoupling Makes Weakly Supervised Local Feature Better [PDF]
, 2022 Weakly supervised learning can help local feature methods to overcome the obstacle of acquiring a large-scale dataset with densely labeled correspondences.
Liu, Li +5 more
core +3 more sources
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
Local Boosting for Weakly-Supervised Learning
Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023 Accepted by KDD 2023 Research ...
Rongzhi Zhang +4 more
openaire +2 more sources
From Weakly Supervised Learning to Biquality Learning: an Introduction [PDF]
2021 International Joint Conference on Neural Networks (IJCNN), 2021 The field of Weakly Supervised Learning (WSL) has recently seen a surge of popularity, with numerous papers addressing different types of "supervision deficiencies". In WSL use cases, a variety of situations exists where the collected "information" is imperfect. The paradigm of WSL attempts to list and cover these problems with associated solutions. In
Nodet, Pierre +4 more
openaire +3 more sources