Filters








2 Hits in 0.47 sec

DeepSetNet: Predicting Sets with Deep Neural Networks [article]

S. Hamid Rezatofighi, Vijay Kumar B G, Anton Milan, Ehsan Abbasnejad, Anthony Dick, Ian Reid
2017 arXiv   pre-print
We define a likelihood for a set distribution and learn its parameters using a deep neural network. We also derive a loss for predicting a discrete distribution corresponding to set cardinality.  ...  This paper addresses the task of set prediction using deep learning.  ...  neural network.  ... 
arXiv:1611.08998v5 fatcat:xe4eo3yqfnhkfic36mbf3p544y

A new fine‐grained method for automated visual analysis of herbarium specimens: A case study for phenological data extraction

Hervé Goëau, Adán Mora‐Fallas, Julien Champ, Natalie L. Rossington Love, Susan J. Mazer, Erick Mata‐Montero, Alexis Joly, Pierre Bonnet
2020 Applications in Plant Sciences  
We adjusted the hyperparameters of a mask R-CNN (regional convolutional neural network) to this specific task and evaluated the resulting trained models for their ability to count reproductive structures  ...  We used a training data set of 21 digitized herbarium sheets for which the position and outlines of 1036 reproductive structures were annotated manually.  ...  ACKNOWLEDGMENTS The authors thank the organizers of the iDigBio Phenology Deep Learning Workshop, which has allowed us to invest deeply in this research topic, and Jean-François Molino for his ideas during  ... 
doi:10.1002/aps3.11368 pmid:32626610 pmcid:PMC7328656 fatcat:bwed35zxdzcbnoiehr7r5almai