A Comparative Study for Open Set Semantic Segmentation Methods

Anderson, Brian; Gutoski, Matheus; Lazzaretti, André E.; Lopes, Heitor Silvério

doi:10.21528/cbic2021-65

Cited by 7 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these approaches are still vulnerable to feature collapse [ 22 ]. We direct the reader to [ 64 , 65 ] for a broader overview of open-set recognition. Open-world approaches attempt to disentangle the detected unknown concepts towards new semantic classes.…”

Section: Related Workmentioning

confidence: 99%

Dense Out-of-Distribution Detection by Robust Learning on Synthetic Negative Data

Grcić,

Bevandić,

Kalafatić

et al. 2024

Sensors

View full text Add to dashboard Cite

Standard machine learning is unable to accommodate inputs which do not belong to the training distribution. The resulting models often give rise to confident incorrect predictions which may lead to devastating consequences. This problem is especially demanding in the context of dense prediction since input images may be only partially anomalous. Previous work has addressed dense out-of-distribution detection by discriminative training with respect to off-the-shelf negative datasets. However, real negative data may lead to over-optimistic evaluation due to possible overlap with test anomalies. To this end, we extend this approach by generating synthetic negative patches along the border of the inlier manifold. We leverage a jointly trained normalizing flow due to a coverage-oriented learning objective and the capability to generate samples at different resolutions. We detect anomalies according to a principled information-theoretic criterion which can be consistently applied through training and inference. The resulting models set the new state of the art on benchmarks for out-of-distribution detection in road-driving scenes and remote sensing imagery despite minimal computational overhead.

show abstract

Section: Related Workmentioning

confidence: 99%

Dense Out-of-Distribution Detection by Robust Learning on Synthetic Negative Data

Grcić,

Bevandić,

Kalafatić

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…OSS is an inherently harder problem due to its dense labeling nature compared to Openset Recognition or Classification. Thus, in real-world scenarios, it is harder to perform open-set semantic segmentation precisely (Brilhador et al, 2021). The complexity of the problem may explain why there is still a gap in the literature, with only a handful of articles tackling the issue (Cui et al, 2020).…”

Section: Introductionmentioning

confidence: 99%