activity
20192022
most citedWeakly Supervised Few-Shot Segmentation Via Meta-Learning

1 citations · 2 across the 3 of their papers we have counts for

collaborators

8 papers

cs.CV20221 cited

Conditional Reconstruction for Open-set Semantic Segmentation

Ian Nunes, Matheus B. Pereira, Hugo Oliveira +2

Open set segmentation is a relatively new and unexploredtask, with just a handful of methods proposed to model suchtasks.We propose a novel method called CoReSeg thattackles the is…

cs.CV20211 cited

Weakly Supervised Few-Shot Segmentation Via Meta-Learning

Pedro H. T. Gama, Hugo Oliveira, José Marcato Junior +1

Semantic segmentation is a classic computer vision task with multiple applications, which includes medical and remote sensing image analysis. Despite recent advances with deep-base…

cs.CV2021

Learning to Segment Medical Images from Few-Shot Sparse Labels

Pedro H. T. Gama, Hugo Oliveira, Jefersson A. dos Santos

In this paper, we propose a novel approach for few-shot semantic segmentation with sparse labeled images. We investigate the effectiveness of our method, which is based on the Mode…

cs.CV2021

Opening Deep Neural Networks with Generative Models

Marcos Vendramini, Hugo Oliveira, Alexei Machado +1

Image classification methods are usually trained to perform predictions taking into account a predefined group of known classes. Real-world problems, however, may not allow for a f…

cs.CV2020

AiRound and CV-BrCT: Novel Multi-View Datasets for Scene Classification

Gabriel Machado, Edemir Ferreira, Keiller Nogueira +3

It is undeniable that aerial/satellite images can provide useful information for a large variety of tasks. But, since these images are always looking from above, some applications…

cs.CV2020

Fully Convolutional Open Set Segmentation

Hugo Oliveira, Caio Silva, Gabriel L. S. Machado +2

In semantic segmentation knowing about all existing classes is essential to yield effective results with the majority of existing approaches. However, these methods trained in a Cl…