Search Results for author: Hugo Oliveira

Found 9 papers, 7 papers with code

Meta-Learners for Few-Shot Weakly-Supervised Medical Image Segmentation

1 code implementation11 May 2023 Hugo Oliveira, Pedro H. T. Gama, Isabelle Bloch, Roberto Marcondes Cesar Jr

Most uses of Meta-Learning in visual recognition are very often applied to image classification, with a relative lack of works in other tasks {such} as segmentation and detection.

Image Classification Image Segmentation +6

FuSS: Fusing Superpixels for Improved Segmentation Consistency

1 code implementation6 Jun 2022 Ian Nunes, Matheus B. Pereira, Hugo Oliveira, Jefersson A. dos Santos, Marcus Poggi

In this work, we propose two different approaches to improve the semantic consistency of Open Set Semantic Segmentation.

Semantic Segmentation Superpixels

Conditional Reconstruction for Open-set Semantic Segmentation

1 code implementation2 Mar 2022 Ian Nunes, Matheus B. Pereira, Hugo Oliveira, Jefersson A. dos Santos, Marcus Poggi

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 issue using class conditional reconstruction ofthe input images according to their pixelwise mask.

Semantic Segmentation

Weakly Supervised Few-Shot Segmentation Via Meta-Learning

no code implementations3 Sep 2021 Pedro H. T. Gama, Hugo Oliveira, José Marcato Junior, Jefersson A. dos Santos

Semantic segmentation is a classic computer vision task with multiple applications, which includes medical and remote sensing image analysis.

Few-Shot Semantic Segmentation Meta-Learning +2

Opening Deep Neural Networks with Generative Models

1 code implementation20 May 2021 Marcos Vendramini, Hugo Oliveira, Alexei Machado, Jefersson A. dos Santos

Image classification methods are usually trained to perform predictions taking into account a predefined group of known classes.

Image Classification Object Recognition +1

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

no code implementations3 Aug 2020 Gabriel Machado, Edemir Ferreira, Keiller Nogueira, Hugo Oliveira, Pedro Gama, Jefersson A. dos Santos

Despite a large number of public repositories for both georeferenced photographs and aerial images, there is a lack of benchmark datasets that allow the development of approaches that exploit the benefits and complementarity of aerial/ground imagery.

General Classification Image Classification +1

Fully Convolutional Open Set Segmentation

1 code implementation25 Jun 2020 Hugo Oliveira, Caio Silva, Gabriel L. S. Machado, Keiller Nogueira, Jefersson A. dos Santos

In semantic segmentation knowing about all existing classes is essential to yield effective results with the majority of existing approaches.

Open Set Learning Segmentation +1

Truly Generalizable Radiograph Segmentation with Conditional Domain Adaptation

1 code implementation16 Jan 2019 Hugo Oliveira, Edemir Ferreira, Jefersson A. dos Santos

We merge these unsupervised networks with supervised deep semantic segmentation architectures in order to create a semi-supervised method capable of learning from both unlabeled and labeled data, whenever labeling is available.

General Classification Segmentation +4

Cannot find the paper you are looking for? You can Submit a new open access paper.