Towards open-set object detection and discovery
With the human pursuit of knowledge, open-set object detection (OSOD) has been designed
to identify unknown objects in a dynamic world. However, an issue with the current setting is …
to identify unknown objects in a dynamic world. However, an issue with the current setting is …
Residual pattern learning for pixel-wise out-of-distribution detection in semantic segmentation
Semantic segmentation models classify pixels into a set of known (" in-distribution") visual
classes. When deployed in an open world, the reliability of these models depends on their …
classes. When deployed in an open world, the reliability of these models depends on their …
Patient centric trustworthy AI in medical analysis and disease prediction: A Comprehensive survey and taxonomy
Artificial Intelligence (AI) integration in healthcare is revolutionizing medical analysis and
disease prediction, enhancing diagnostic accuracy and patient care. However, with the …
disease prediction, enhancing diagnostic accuracy and patient care. However, with the …
Fuzzy inference algorithm for quantifying thermal comfort in peri-urban environments
RC Santos, R Baréa, AC Sanches… - Environment …, 2024 - Springer
The alteration of the landscape due to urban concentration can bring effects such as “heat
islands” that affect human well-being. The objective was to apply mathematical modeling …
islands” that affect human well-being. The objective was to apply mathematical modeling …
TRL: Transformer based refinement learning for hybrid-supervised semantic segmentation
This paper studies a new yet practical setting of semi-supervised semantic segmentation, ie,
hybrid-supervised semantic segmentation, where a small number of pixel-level (strong) …
hybrid-supervised semantic segmentation, where a small number of pixel-level (strong) …
A prototypical metric learning approach for open-set semantic segmentation on remote sensing images
A Brilhador, AE Lazzaretti… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Semantic segmentation has received wide attention as a feasible solution to effectively
interpret the information in remote sensing images. Solutions are typically built with a static …
interpret the information in remote sensing images. Solutions are typically built with a static …
Curved geometric networks for visual anomaly recognition
Learning a latent embedding to understand the underlying nature of data distribution is often
formulated in Euclidean spaces with zero curvature. However, the success of the geometry …
formulated in Euclidean spaces with zero curvature. However, the success of the geometry …
Segmenting known objects and unseen unknowns without prior knowledge
S Gasperini, A Marcos-Ramiro… - Proceedings of the …, 2023 - openaccess.thecvf.com
Panoptic segmentation methods assign a known class to each pixel given in input. Even for
state-of-the-art approaches, this inevitably enforces decisions that systematically lead to …
state-of-the-art approaches, this inevitably enforces decisions that systematically lead to …
Open-Set Tattoo Semantic Segmentation
A Brilhador, RT Da Silva, CR Modinez-Junior… - IEEE …, 2024 - ieeexplore.ieee.org
Tattoos can serve as an essential source of biometric information for public security, aiding
in identifying suspects and victims. In order to automate tattoo classification, tasks like …
in identifying suspects and victims. In order to automate tattoo classification, tasks like …
Class Semantics Modulation for Open-Set Instance Segmentation
This letter addresses the challenge of open-set instance segmentation (OSIS) which
segments both known objects and unknown objects not seen in training, and thus is …
segments both known objects and unknown objects not seen in training, and thus is …