1 citations · 1 across the 2 of their papers we have counts for
8 papers
Domain Generalization by Rejecting Extreme Augmentations
Masih Aminbeidokhti, Fidel A. Guerrero Peña, Heitor Rapela Medeiros +3
Data augmentation is one of the most effective techniques for regularizing deep learning models and improving their recognition performance in a variety of tasks and domains. Howev…
HalluciDet: Hallucinating RGB Modality for Person Detection Through Privileged Information
Heitor Rapela Medeiros, Fidel A. Guerrero Pena, Masih Aminbeidokhti +3
A powerful way to adapt a visual recognition model to a new domain is through image translation. However, common image translation approaches only focus on generating data from the…
J Regularization Improves Imbalanced Multiclass Segmentation
Fidel A. Guerrero Peña, Pedro D. Marrero Fernandez, Paul T. Tarr +3
We propose a new loss formulation to further advance the multiclass segmentation of cluttered cells under weakly supervised conditions. We improve the separation of touching and im…
A Multiple Source Hourglass Deep Network for Multi-Focus Image Fusion
Fidel Alejandro Guerrero Peña, Pedro Diamel Marrero Fernández, Tsang Ing Ren +2
Multi-Focus Image Fusion seeks to improve the quality of an acquired burst of images with different focus planes. For solving the task, an activity level measurement and a fusion r…
A Weakly Supervised Method for Instance Segmentation of Biological Cells
Fidel A. Guerrero-Peña, Pedro D. Marrero Fernandez, Tsang Ing Ren +1
We present a weakly supervised deep learning method to perform instance segmentation of cells present in microscopy images. Annotation of biomedical images in the lab can be scarce…
FERAtt: Facial Expression Recognition with Attention Net
Pedro D. Marrero Fernandez, Fidel A. Guerrero Peña, Tsang Ing Ren +1
We present a new end-to-end network architecture for facial expression recognition with an attention model. It focuses attention in the human face and uses a Gaussian space represe…