Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Rodrigo F. Berriel

Copycat CNN: Are Random Non-Labeled Data Enough to Steal Knowledge from Black-box Models?


Jan 21, 2021
Jacson Rodrigues Correia-Silva, Rodrigo F. Berriel, Claudine Badue, Alberto F. De Souza, Thiago Oliveira-Santos

* Pattern Recognition 113 (2021) 107830 
* The code is available at https://github.com/jeiks/Stealing_DL_Models 

  Access Paper or Ask Questions

Deep traffic light detection by overlaying synthetic context on arbitrary natural images


Nov 10, 2020
Jean Pablo Vieira de Mello, Lucas Tabelini, Rodrigo F. Berriel, Thiago M. Paixão, Alberto F. de Souza, Claudine Badue, Nicu Sebe, Thiago Oliveira-Santos

* Computers & Graphics (2020) 

  Access Paper or Ask Questions

Self-supervised Deep Reconstruction of Mixed Strip-shredded Text Documents


Jul 01, 2020
Thiago M. Paixão, Rodrigo F. Berriel, Maria C. S. Boeres, Alessandro L. Koerich, Claudine Badue, Alberto F. de Souza, Thiago Oliveira-Santos

* Accepted for publication in Pattern Recognition 

  Access Paper or Ask Questions

Fast(er) Reconstruction of Shredded Text Documents via Self-Supervised Deep Asymmetric Metric Learning


Apr 29, 2020
Thiago M. Paixão, Rodrigo F. Berriel, Maria C. S. Boeres, Alessando L. Koerich, Claudine Badue, Alberto F. De Souza, Thiago Oliveira-Santos

* Accepted to CVPR 2020. Main Paper (9 pages, 10 figures) and Supplementary Material (5 pages, 9 figures) 

  Access Paper or Ask Questions

Effortless Deep Training for Traffic Sign Detection Using Templates and Arbitrary Natural Images


Jul 23, 2019
Lucas Tabelini Torres, Thiago M. Paixão, Rodrigo F. Berriel, Alberto F. De Souza, Claudine Badue, Nicu Sebe, Thiago Oliveira-Santos


  Access Paper or Ask Questions

Cross-Domain Car Detection Using Unsupervised Image-to-Image Translation: From Day to Night


Jul 19, 2019
Vinicius F. Arruda, Thiago M. Paixão, Rodrigo F. Berriel, Alberto F. De Souza, Claudine Badue, Nicu Sebe, Thiago Oliveira-Santos

* 8 pages, 8 figures, https://github.com/viniciusarruda/cross-domain-car-detection and accepted at IJCNN 2019 

  Access Paper or Ask Questions

Traffic Light Recognition Using Deep Learning and Prior Maps for Autonomous Cars


Jun 04, 2019
Lucas C. Possatti, Rânik Guidolini, Vinicius B. Cardoso, Rodrigo F. Berriel, Thiago M. Paixão, Claudine Badue, Alberto F. De Souza, Thiago Oliveira-Santos

* Accepted in 2019 International Joint Conference on Neural Networks (IJCNN) 

  Access Paper or Ask Questions

Ego-Lane Analysis System (ELAS): Dataset and Algorithms


Jun 15, 2018
Rodrigo F. Berriel, Edilson de Aguiar, Alberto F. de Souza, Thiago Oliveira-Santos

* Image and Vision Computing 68 (2017) 64-75 
* 13 pages, 17 figures, github.com/rodrigoberriel/ego-lane-analysis-system, and published by Image and Vision Computing (IMAVIS) 

  Access Paper or Ask Questions

Copycat CNN: Stealing Knowledge by Persuading Confession with Random Non-Labeled Data


Jun 14, 2018
Jacson Rodrigues Correia-Silva, Rodrigo F. Berriel, Claudine Badue, Alberto F. de Souza, Thiago Oliveira-Santos

* 8 pages, 3 figures, accepted by IJCNN 2018 

  Access Paper or Ask Questions

Automatic Large-Scale Data Acquisition via Crowdsourcing for Crosswalk Classification: A Deep Learning Approach


May 30, 2018
Rodrigo F. Berriel, Franco Schmidt Rossi, Alberto F. de Souza, Thiago Oliveira-Santos

* Computers & Graphics, 2017, vol. 68, pp. 32-42 
* 13 pages, 13 figures, 3 videos, and GitHub with models 

  Access Paper or Ask Questions

Deep Learning Based Large-Scale Automatic Satellite Crosswalk Classification


Jul 05, 2017
Rodrigo F. Berriel, Andre Teixeira Lopes, Alberto F. de Souza, Thiago Oliveira-Santos

* 5 pages, 3 figures, accepted by IEEE Geoscience and Remote Sensing Letters 

  Access Paper or Ask Questions