paper-with-me

Papers

Towards Robust Object Detection: Bayesian RetinaNet for Homoscedastic Aleatoric Uncertainty Modeling

2021-08-02 · Natalia Khanzhina, Alexey Lapenok, Andrey Filchenkov

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.

📄 PDF Abstract BibTeX arXiv:2108.00784

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian InferenceObjectobject-detectionObject DetectionRobust Object Detection

Methods 이 논문이 사용한 방법론

FPN 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Focal Loss A Focal Loss function addresses class imbalance during training in tasks like object detection. Focal loss applies a modulating term to the cross entropy loss in order to…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
RetinaNet RetinaNet is a one-stage object detection model that utilizes a focal loss function to address class imbalance during training.…

Similar Papers 제목 키워드 기반

Antifragile and Robust Heteroscedastic Bayesian Optimisation

2019-09-25 · Ryan Rhys-Griffiths, Miguel Garcia-Ortegon, Alexander A. Aldrick, Alpha A. Lee

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 Discovery

Achieving Robustness to Aleatoric Uncertainty with Heteroscedastic Bayesian Optimisation

2019-10-17 · Ryan-Rhys Griffiths, Alexander A. Aldrick, Miguel Garcia-Ortegon, Vidhi R. Lalchand 외

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 Discovery

Heteroscedastic Preferential Bayesian Optimization with Informative Noise Distributions

2024-05-23 · Marshal Arijona Sinaga, Julien Martinelli, Vikas Garg, Samuel Kaski

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 OptimizationInformativeness

Bayesian OOD detection with aleatoric uncertainty and outlier exposure

2021-02-24 · pproximateinference AABI Symposium 2022 2 · Xi Wang, Laurence Aitchison

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) Detection

Heteroscedastic Neural Surrogate Modeling for Robust and Rapid Bayesian Inference in Fusion Plasma Diagnostics

2026-08-19 · Liyun Zhang, Naoya Mamada, Kentaro Sakai, Takeo Hoshi 외 arxiv

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