mlsanityData to 13 Oct 2026

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

arXiv 2108.00784 ↗First posted 2 Aug 2021cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 27 of its 32 references that are in the map. First posted on arXiv 2 Aug 2021.

Builds on

27 of 32 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,093
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,223
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,550
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,321
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,426
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,027
  8. 2015Fast R-CNNcited by 2,933
  9. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,340
  10. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,348
  11. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 910
  12. 2017Focal Loss for Dense Object Detectioncited by 750
15 more
  1. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
  2. 2015Towards Open Set Deep Networkscited by 535
  3. 2021Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarkscited by 391
  4. 2019LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Drivingcited by 133
  5. 2017Dropout Sampling for Robust Object Detection in Open-Set Conditionscited by 112
  6. 2018Towards Safe Autonomous Driving: Capture Uncertainty in the Deep Neural Network For Lidar 3D Vehicle Detectioncited by 82
  7. 2017Toward Robustness against Label Noise in Training Deep Discriminative Neural Networkscited by 78
  8. 2019Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagationcited by 74
  9. 2019BayesOD: A Bayesian Approach for Uncertainty Estimation in Deep Object Detectorscited by 68
  10. 2018Evaluating Merging Strategies for Sampling-based Uncertainty Techniques in Object Detectioncited by 51
  11. 2017Learning From Noisy Singly-labeled Datacited by 50
  12. 2019SpineNet: Learning Scale-Permuted Backbone for Recognition and Localizationcited by 50
  13. 2019Uncertainty Estimation in One-Stage Object Detectioncited by 36
  14. 2021Uncertainty for Identifying Open-Set Errors in Visual Object Detectioncited by 26
  15. 2018Leveraging Heteroscedastic Aleatoric Uncertainties for Robust Real-Time LiDAR 3D Object Detectioncited by 19

Built on by

Not cited yet.