Towards Robust Object Detection: Bayesian RetinaNet for Homoscedastic Aleatoric Uncertainty Modeling
According to recent studies, commonly used computer vision datasets contain about 4% of label errors. For example, the COCO dataset is known for its high level of noise in data labels, which limits its use for training robust neural deep architectures in a real-world scenario. To model such a noise, in this paper we have proposed the homoscedastic aleatoric uncertainty estimation, and present a series of novel loss functions to address the problem of image object detection at scale. Specifically, the proposed functions are based on Bayesian inference and we have incorporated them into the common community-adopted object detection deep learning architecture RetinaNet. We have also shown that modeling of homoscedastic aleatoric uncertainty using our novel functions allows to increase the model interpretability and to improve the object detection performance being evaluated on the COCO dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
Bayesian InferenceObjectobject-detectionObject DetectionRobust Object DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Antifragile and Robust Heteroscedastic Bayesian Optimisation
Bayesian Optimisation is an important decision-making tool for high-stakes applications in drug discovery and materials design. An oft-overlooked modelling consideration however is the representation of input-depende…
Bayesian OptimisationDecision MakingDrug DiscoveryAchieving Robustness to Aleatoric Uncertainty with Heteroscedastic Bayesian Optimisation
Bayesian optimisation is a sample-efficient search methodology that holds great promise for accelerating drug and materials discovery programs. A frequently-overlooked modelling consideration in Bayesian optimisation str…
Bayesian OptimisationDecision MakingDrug DiscoveryHeteroscedastic Preferential Bayesian Optimization with Informative Noise Distributions
Preferential Bayesian optimization (PBO) is a sample-efficient framework for learning human preferences between candidate designs. PBO classically relies on homoscedastic noise models to represent human aleatoric uncerta…
Bayesian OptimizationInformativenessBayesian OOD detection with aleatoric uncertainty and outlier exposure
Typical Bayesian approaches to OOD detection use epistemic uncertainty. Surprisingly from the Bayesian perspective, there are a number of methods that successfully use aleatoric uncertainty to detect OOD points (e.g. Hen…
Out-of-Distribution DetectionOut of Distribution (OOD) DetectionHeteroscedastic Neural Surrogate Modeling for Robust and Rapid Bayesian Inference in Fusion Plasma Diagnostics
Bayesian inference via Markov Chain Monte Carlo (MCMC) provides effective parameter estimation, but its real-time application in complex physical systems is hindered by heavy computational bottlenecks and extreme sensiti…
Bayesian Inference