CertainNet: Sampling-Free Uncertainty Estimation for Object Detection

Gasperini, Stefano; Haug, Jan; Mahani, Mohammad-Ali Nikouei; Marcos-Ramiro, Alvaro; Navab, Nassir; Busam, Benjamin; Tombari, Federico

doi:10.1109/lra.2021.3130976

Cited by 22 publications

(12 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Achieving high accuracy in object detection is crucial for the overall safety and success of autonomous driving systems. To address this problem Gasperini et al [258] proposed CertainNet to estimate the uncertainty of the outputs (presence of object, and its class, location and size). They used KITTI dataset to train the model.…”

Section: Cameramentioning

confidence: 99%

Recent Advancements in Deep Learning Applications and Methods for Autonomous Navigation -- A Comprehensive Review

Golroudbari¹,

Sabour²

2023

Preprint

View full text Add to dashboard Cite

This review paper presents a comprehensive overview of end-to-end deep learning frameworks used in the context of autonomous navigation, including obstacle detection, scene perception, path planning, and control. The paper aims to bridge the gap between autonomous navigation and deep learning by analyzing recent research studies and evaluating the implementation and testing of deep learning methods. It emphasizes the importance of navigation for mobile robots, autonomous vehicles, and unmanned aerial vehicles, while also acknowledging the challenges due to environmental complexity, uncertainty, obstacles, dynamic environments, and the need to plan paths for multiple agents. The review highlights the rapid growth of deep learning in engineering data science and its development of innovative navigation methods. It discusses recent interdisciplinary work related to this field and provides a brief perspective on the limitations, challenges, and potential areas of growth for deep learning methods in autonomous navigation. Finally, the paper summarizes the findings and practices at different stages, correlating existing and future methods, their applicability, scalability, and limitations. The review provides a valuable resource for researchers and practitioners working in the field of autonomous navigation and deep learning.

show abstract

Section: Cameramentioning

confidence: 99%

Recent Advancements in Deep Learning Applications and Methods for Autonomous Navigation -- A Comprehensive Review

Golroudbari¹,

Sabour²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The most related work is CertainNet [2] since they also extend the CenterNet [26] object detector by computing the uncertainties in a single forward pass. Differently from us, the uncertainty estimation is based on the DUQ method [11].…”

Section: Related Workmentioning

confidence: 99%

“…However, extensive time and computation requirements render such methods less usable for applications such as autonomous driving. Other methods use sampling-free approaches, including only predicting either the classification or regression uncertainty, involving modifications to the convolution kernels and complex post-processing steps for obtaining the uncertainties [2]. Moreover, there is generally a loss of detection accuracy, given an overhead task of uncertainty estimation on top of object detection.…”

Section: Introductionmentioning

confidence: 99%

EvCenterNet: Uncertainty Estimation for Object Detection using Evidential Learning

Nallapareddy¹,

Sirohi²,

Drews-Jr³

et al. 2023

Preprint

View full text Add to dashboard Cite

Uncertainty estimation is crucial in safety-critical settings such as automated driving as it provides valuable information for several downstream tasks including high-level decision-making and path planning. In this work, we propose EvCenterNet, a novel uncertainty-aware 2D object detection framework utilizing evidential learning to directly estimate both classification and regression uncertainties. To employ evidential learning for object detection, we devise a combination of evidential and focal loss functions for the sparse heatmap inputs. We introduce class-balanced weighting for regression and heatmap prediction to tackle the class imbalance encountered by evidential learning. Moreover, we propose a learning scheme to actively utilize the predicted heatmap uncertainties to improve the detection performance by focusing on the most uncertain points. We train our model on the KITTI dataset and evaluate it on challenging out-of-distribution datasets including BDD100K and nuImages. Our experiments demonstrate that our approach improves the precision and minimizes the execution time loss in relation to the base model.

show abstract

“…Nevertheless, some methods focus in uncertainty on regressing the bounding boxes [8,19]. [18] propose a sample free approach to estimate the uncertainty in both bounding box regression and the objectness for realtime application. Recently, [13] propose a method for 2D out-of-distribution detection by generating outliers in the feature space.…”

Section: Related Workmentioning

confidence: 99%

Instance-Aware Observer Network for Out-of-Distribution Object Segmentation

Besnier¹,

Bursuc²,

Picard³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recent work on Observer Network has shown promising results on Out-Of-Distribution (OOD) detection for semantic segmentation. These methods have difficulty in precisely locating the point of interest in the image, i.e, the anomaly. This limitation is due to the difficulty of fine-grained prediction at the pixel level. To address this issue, we provide instance knowledge to the observer. We extend the approach of ObsNet by harnessing an instance-wise mask prediction. We use an additional, class agnostic, object detector to filter and aggregate observer predictions. Finally, we predict an unique anomaly score for each instance in the image. We show that our proposed method accurately disentangle in-distribution objects from Out-Of-Distribution objects on three datasets.

show abstract

CertainNet: Sampling-Free Uncertainty Estimation for Object Detection

Cited by 22 publications

References 21 publications

Recent Advancements in Deep Learning Applications and Methods for Autonomous Navigation -- A Comprehensive Review

Recent Advancements in Deep Learning Applications and Methods for Autonomous Navigation -- A Comprehensive Review

EvCenterNet: Uncertainty Estimation for Object Detection using Evidential Learning

Instance-Aware Observer Network for Out-of-Distribution Object Segmentation

Contact Info

Product

Resources

About