Filters








3 Hits in 1.7 sec

Towards Automated Computer Vision: Analysis of the AutoCV Challenges 2019

Zhengying Liu, Zhen Xu, Sergio Escalera, Isabelle Guyon, Julio C.S. Jacques Junior, Meysam Madadi, Adrien Pavao, Sebastien Treguer, Wei-Wei Tu
2020 Pattern Recognition Letters  
We present the results of recent challenges in Automated Computer Vision (AutoCV, renamed here for clarity AutoCV1 and AutoCV2, 2019), which are part of a series of challenge on Automated Deep Learning  ...  These two competitions aim at searching for fully automated solutions for classification tasks in computer vision, with an emphasis on any-time performance.  ...  We present here the results of the two first editions of the Automated Deep Learning (AutoDL) challenge series, addressing Automated Computer Vision (AutoCV).  ... 
doi:10.1016/j.patrec.2020.04.030 fatcat:6kxx32nj4nddjpireu3j4qvsye

AutoML Meets Time Series Regression Design and Analysis of the AutoSeries Challenge [article]

Zhen Xu, Wei-Wei Tu, Isabelle Guyon
2021 arXiv   pre-print
Driven by business scenarios, we organized the first Automated Time Series Regression challenge (AutoSeries) for the WSDM Cup 2020. We present its design, analysis, and post-hoc experiments.  ...  Simple yet effective methods were used, based on feature engineering, LightGBM, and random search hyper-parameter tuning, addressing all aspects of the challenge.  ...  Towards automated computer vision: analysis of the autocv challenges 2019. Pattern Recognit. Lett., 2020.  ... 
arXiv:2107.13186v2 fatcat:nzufsf3qg5bqbcu4kgkylebhbe

Winning solutions and post-challenge analyses of the ChaLearn AutoDL challenge 2019

Zhengying Liu, Adrien Pavao, Zhen Xu, Sergio Escalera, Fabio Ferreira, Isabelle Guyon, Sirui Hong, Frank Hutter, Rongrong Ji, Julio C. S. Jacques Junior, Ge Li, Marius Lindauer (+13 others)
2022
This paper reports the results and post-challenge analyses of ChaLearn's AutoDL challenge series, which helped sorting out a profusion of AutoML solutions for Deep Learning (DL) that had been introduced  ...  Our challenge legacy includes an ever-lasting benchmark (http://autodl.chalearn.org), the open-sourced code of the winners, and a free "AutoDL self-service".  ...  He leads the Human Behavior Analysis Group at UB and Computer Vision Center. He is series editor of The Springer Series on Challenges in Machine Learning.  ... 
doi:10.48550/arxiv.2201.03801 fatcat:635c6lbe6baj5gdoqqy52xcome