Results 61 to 70 of about 76,480 (326)

Weakly Supervised Audio Source Separation via Spectrum Energy Preserved Wasserstein Learning

, 2018
Separating audio mixtures into individual instrument tracks has been a long standing challenging task. We introduce a novel weakly supervised audio source separation approach based on deep adversarial learning.
Yan, Junchi, Zhang, Ning, Zhou, Yuchen
core   +1 more source

In vitro models of cancer‐associated fibroblast heterogeneity uncover subtype‐specific effects of CRISPR perturbations

Molecular Oncology, EarlyView.
Development of therapies targeting cancer‐associated fibroblasts (CAFs) necessitates preclinical model systems that faithfully represent CAF–tumor biology. We established an in vitro coculture system of patient‐derived pancreatic CAFs and tumor cell lines and demonstrated its recapitulation of primary CAF–tumor biology with single‐cell transcriptomics ...
Elysia Saputra, Shamsudheen Karuthedath Vellarikkal, Lixia Li, Hong Sun, Khoa Nguyen, Amber Montano, Suchitra Natarajan, Federica Piccioni, Alex Michael Tamburino, Xin Yu, Aleksandra Katarzyna Olow   +10 more
wiley   +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, Yue Yu, Jiaming Shen, Xiquan Cui, Chao Zhang   +4 more
openaire   +2 more sources

A Weakly Supervised and Self-Supervised Learning Approach for Semantic Segmentation of Land Cover in Satellite Images with National Forest Inventory Data

Remote Sensing
National Forest Inventories (NFIs) provide valuable land cover (LC) information but often lack spatial continuity and an adequate update frequency. Satellite-based remote sensing offers a viable alternative, employing machine learning to extract thematic
Daniel Moraes, Manuel L. Campagnolo, Mário Caetano   +2 more
doaj   +1 more source

PistonNet: Object Separating From Background by Attention for Weakly Supervised Ship Detection

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022
Object detection under weakly supervised learning is a challenging issue. In a remote sensing ship detection task, the weakly supervised learning method requires that the training set only has image-level class annotations.
Yi Yang, Zongxu Pan, Yuxin Hu, Chibiao Ding   +3 more
doaj   +1 more source

Genetic attenuation of ALDH1A1 increases metastatic potential and aggressiveness in colorectal cancer

Molecular Oncology, EarlyView.
Aldehyde dehydrogenase 1A1 (ALDH1A1) is a cancer stem cell marker in several malignancies. We established a novel epithelial cell line from rectal adenocarcinoma with unique overexpression of this enzyme. Genetic attenuation of ALDH1A1 led to increased invasive capacity and metastatic potential, the inhibition of proliferation activity, and ultimately ...
Martina Poturnajova, Zuzana Kozovska, Ondrej Pos, Kristina Pavlov, Sachin Gulati, Peter Makovicky, Kristina Jakic, Monika Burikova, Eva Sedlackova, Barbora Svitkova, Silvia Tyciakova, Vojtech Bystry, Nicolas Blavet, Boris Tichy, Matej Hrnciar, Jaroslav Budis, Miroslav Tomas, Peter Dubovan, Georgina Kolnikova, Veronika Repaska, Nikoleta Mojzesova, Eva Zomborska, Daniel Pindak, Michal Mego, Tomas Szemes, Miroslava Matuskova   +25 more
wiley   +1 more source

Learning Consistency From High-Confidence Pseudo-Labels for Weakly Supervised Object Localization

IEEE Access, 2023
Weakly supervised object localization (WSOL) tasks aim to classify and locate a single object under the supervision of only image-level labels. Pseudo-supervised learning methods have been shown to be effective for WSOL.
Kangbo Sun, Jie Zhu
doaj   +1 more source

Two-Phase Learning for Weakly Supervised Object Localization

, 2017
Weakly supervised semantic segmentation and localiza- tion have a problem of focusing only on the most important parts of an image since they use only image-level annota- tions.
Cho, Donghyeon, Kim, Dahun, Kweon, In So, Yoo, Donggeun   +3 more
core   +1 more source

Overview of molecular signatures of senescence and associated resources: pros and cons

FEBS Open Bio, EarlyView.
Cells can enter a stress response state termed cellular senescence that is involved in various diseases and aging. Detecting these cells is challenging due to the lack of universal biomarkers. This review presents the current state of senescence identification, from biomarkers to molecular signatures, compares tools and approaches, and highlights ...
Orestis A. Ntintas, Sylvia Vagena, Pavlos Pantelis, Giorgos Theocharous, Russel Petty, Konstantinos Evangelou, Vassilis G. Gorgoulis   +6 more
wiley   +1 more source

Multimodal Visual Concept Learning with Weakly Supervised Techniques

, 2018
Despite the availability of a huge amount of video data accompanied by descriptive texts, it is not always easy to exploit the information contained in natural language in order to automatically recognize video concepts.
Bouritsas, Giorgos, Koutras, Petros, Maragos, Petros, Zlatintsi, Athanasia   +3 more
core   +1 more source