Ian Nunes - Academia.edu (original) (raw)

Ian Nunes

Uploads

Papers by Ian Nunes

Research paper thumbnail of FuSS: Fusing Superpixels for Improved Segmentation Consistency

arXiv (Cornell University), Jun 6, 2022

In this work, we propose two different approaches to improve the semantic consistency of Open Set... more In this work, we propose two different approaches to improve the semantic consistency of Open Set Semantic Segmentation. First, we propose a method called OpenGMM that extends the OpenPCS framework using a Gaussian Mixture of Models to model the distribution of pixels for each class in a multimodal manner. The second approach is a post-processing which uses superpixels to enforce highly homogeneous regions to behave equally, rectifying erroneous classified pixels within these regions, we also proposed a novel superpixel method called FuSS. All tests were performed on ISPRS Vaihingen and Potsdam datasets, and both methods were capable to improve quantitative and qualitative results for both datasets. Besides that, the post-process with FuSS achieved state-of-the-art results for both datasets. The official implementation is available at: https://github.com/iannunes/FuSS.

Research paper thumbnail of Conditional Reconstruction for Open-Set Semantic Segmentation

2022 IEEE International Conference on Image Processing (ICIP), Oct 16, 2022

Open set segmentation is a relatively new and unexplored task, with just a handful of methods pro... more Open set segmentation is a relatively new and unexplored task, with just a handful of methods proposed to model such tasks. We propose a novel method called CoReSeg that tackles the issue using class conditional reconstruction of the input images according to their pixelwise mask. Our method conditions each input pixel to all known classes, expecting higher errors for pixels of unknown classes. It was observed that the proposed method produces better semantic consistency in its predictions, resulting in cleaner segmentation maps that better fit object boundaries. CoRe-Seg outperforms state-of-the-art methods on the Vaihingen and Potsdam ISPRS datasets, while also being competitive on the Houston 2018 IEEE GRSS Data Fusion dataset. Official implementation for CoReSeg is available at: https://github.com/iannunes/CoReSeg.

Research paper thumbnail of A systematic review on open-set segmentation

Research paper thumbnail of A Systematic Review on Open-Set Semantic Segmentation

Social Science Research Network, 2023

Research paper thumbnail of Open-Set Semantic Segmentation for Remote Sensing Images

Research paper thumbnail of Deep Open-Set Segmentation in Visual Learning

2022 35th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)

Research paper thumbnail of Conditional Reconstruction for Open-set Semantic Segmentation

ArXiv, 2022

Open set segmentation is a relatively new and unexplored task, with just a handful of methods pro... more Open set segmentation is a relatively new and unexplored task, with just a handful of methods proposed to model such tasks. We propose a novel method called CoReSeg that tackles the issue using class conditional reconstruction of the input images according to their pixelwise mask. Our method conditions each input pixel to all known classes, expecting higher errors for pixels of unknown classes. It was observed that the proposed method produces better semantic consistency in its predictions, resulting in cleaner segmentation maps that better fit object boundaries. CoReSeg outperforms state-of-the-art methods on the Vaihingen and Potsdam ISPRS datasets, while also being competitive on the Houston 2018 IEEE GRSS Data Fusion dataset. Official implementation for CoReSeg is available at: https://github.com/iannunes/CoReSeg.

Research paper thumbnail of Agrupamento De Registros Textuais Baseado Em Similaridade Entre Textos

Aprendizado de máquina; mineração de textos; deduplicação; recuperação de informação.

Research paper thumbnail of FuSS: Fusing Superpixels for Improved Segmentation Consistency

arXiv (Cornell University), Jun 6, 2022

In this work, we propose two different approaches to improve the semantic consistency of Open Set... more In this work, we propose two different approaches to improve the semantic consistency of Open Set Semantic Segmentation. First, we propose a method called OpenGMM that extends the OpenPCS framework using a Gaussian Mixture of Models to model the distribution of pixels for each class in a multimodal manner. The second approach is a post-processing which uses superpixels to enforce highly homogeneous regions to behave equally, rectifying erroneous classified pixels within these regions, we also proposed a novel superpixel method called FuSS. All tests were performed on ISPRS Vaihingen and Potsdam datasets, and both methods were capable to improve quantitative and qualitative results for both datasets. Besides that, the post-process with FuSS achieved state-of-the-art results for both datasets. The official implementation is available at: https://github.com/iannunes/FuSS.

Research paper thumbnail of Conditional Reconstruction for Open-Set Semantic Segmentation

2022 IEEE International Conference on Image Processing (ICIP), Oct 16, 2022

Open set segmentation is a relatively new and unexplored task, with just a handful of methods pro... more Open set segmentation is a relatively new and unexplored task, with just a handful of methods proposed to model such tasks. We propose a novel method called CoReSeg that tackles the issue using class conditional reconstruction of the input images according to their pixelwise mask. Our method conditions each input pixel to all known classes, expecting higher errors for pixels of unknown classes. It was observed that the proposed method produces better semantic consistency in its predictions, resulting in cleaner segmentation maps that better fit object boundaries. CoRe-Seg outperforms state-of-the-art methods on the Vaihingen and Potsdam ISPRS datasets, while also being competitive on the Houston 2018 IEEE GRSS Data Fusion dataset. Official implementation for CoReSeg is available at: https://github.com/iannunes/CoReSeg.

Research paper thumbnail of A systematic review on open-set segmentation

Research paper thumbnail of A Systematic Review on Open-Set Semantic Segmentation

Social Science Research Network, 2023

Research paper thumbnail of Open-Set Semantic Segmentation for Remote Sensing Images

Research paper thumbnail of Deep Open-Set Segmentation in Visual Learning

2022 35th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)

Research paper thumbnail of Conditional Reconstruction for Open-set Semantic Segmentation

ArXiv, 2022

Open set segmentation is a relatively new and unexplored task, with just a handful of methods pro... more Open set segmentation is a relatively new and unexplored task, with just a handful of methods proposed to model such tasks. We propose a novel method called CoReSeg that tackles the issue using class conditional reconstruction of the input images according to their pixelwise mask. Our method conditions each input pixel to all known classes, expecting higher errors for pixels of unknown classes. It was observed that the proposed method produces better semantic consistency in its predictions, resulting in cleaner segmentation maps that better fit object boundaries. CoReSeg outperforms state-of-the-art methods on the Vaihingen and Potsdam ISPRS datasets, while also being competitive on the Houston 2018 IEEE GRSS Data Fusion dataset. Official implementation for CoReSeg is available at: https://github.com/iannunes/CoReSeg.

Research paper thumbnail of Agrupamento De Registros Textuais Baseado Em Similaridade Entre Textos

Aprendizado de máquina; mineração de textos; deduplicação; recuperação de informação.

Log In