Título: A Comparative Study for Open Set Semantic Segmentation Methods
Autores: Anderson Brilhador, Matheus Gutoski, André Eugênio Lazzaretti and Heitor Silvério Lopes.
Resumo:
Typical semantic segmentation methods do not recognize unknown pixels during the test or deployment stage. This capability is critical for open-world environment applications where unseen objects appear all the time. Recently, to solve those limitations, Open Set Semantic Segmentation (OSSS) was introduced. This task aims to produce known and unknown pixels semantic segments. However, due to its recent introduction, few works are found in the literature, and consequently, few datasets are publicly available. This work carried out a comparative study between the existing OSSS methods on a new synthetic dataset of images and the well-known PASCAL VOC 2012 dataset. The compared methods include SoftMax-T, OpenMax-based, and OpenIPCS. The results are encouraging and show some of the advantages and main limitations of each technique. However, in general, they demonstrate that the problem of OSSS remains open and demands further research aiming at real applications, such as autonomous driving and robotics.
Palavras-chave:
Open Set Recognition, Open World Problem, Semantic Segmentation, Synthetic Geometry Dataset.
Páginas: 8
Código DOI: 10.21528/CBIC2021-65
Artigo em pdf: CBIC_2021_paper_65.pdf
Arquivo BibTeX: CBIC_2021_65.bib