Open set recognition through Monte Carlo dropout-based uncertainty
نویسندگان
چکیده
منابع مشابه
Active Monte Carlo Recognition
In this paper we introduce Active Monte Carlo Recognition (AMCR), a new approach for object recognition. The method is based on seeding and propagating ”relational” particles that represent hypothetical relations between low-level perception and high-level object knowledge. AMCR acts as a filter with each individual step verifying fragments of different objects, and with the sequence of resulti...
متن کاملUncertainty on fringe projection technique: a Monte-Carlo-based approach
6 Error estimation on optical full field techniques (OFFT) is millstone in the diffusion of OFFT. 7 The present work describes a generic way to estimate overall error in fringe projection, either 8 due to random sources (phase error, basically related to the quality of the camera and of the 9 fringe extraction algorithm) or the bias (calibration errors). Here, a high level calibration 10 proced...
متن کاملMonte-Carlo based uncertainty analysis: Sampling efficiency and sampling convergence
Monte Carlo analysis has become nearly ubiquitous since its introduction, now over 65 years ago. It is an important tool in many assessments of the reliability and robustness of systems, structures or solutions. As the deterministic core simulation can be lengthy, the computational costs of Monte Carlo can be a limiting factor. To reduce that computational expense as much as possible, sampling ...
متن کاملReliable kinetic Monte Carlo simulation based on random set sampling
Kinetic Monte Carlo (KMC) method has been widely used in simulating rare events such as chemical reactions or phase transitions. Yet lack of complete knowledge of transitions and the associated rates is one major challenge for accurate KMC predictions. In this paper, a reliable KMC (R-KMC) mechanism is proposed in which sampling is based on random sets instead of random numbers to improve the r...
متن کاملReasoning Under Uncertainty: Some Monte Carlo Results
A series of monte carlo studies were performed to compare the behavior of some alternative procedures for reasoning under uncertainty. The behavior of several Bayesian, linear model and default reasoning procedures were examined in the context of increasing levels of calibration error. The most interesting result is that Bayesian procedures tended to output more extreme posterior belief values ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: International Journal of Bio-inspired Computation
سال: 2021
ISSN: ['1758-0366', '1758-0374']
DOI: https://doi.org/10.1504/ijbic.2021.10043757