[HTML][HTML] Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysis
The full acceptance of Deep Learning (DL) models in the clinical field is rather low with
respect to the quantity of high-performing solutions reported in the literature. End users are …
respect to the quantity of high-performing solutions reported in the literature. End users are …
Document understanding dataset and evaluation (dude)
J Van Landeghem, R Tito… - Proceedings of the …, 2023 - openaccess.thecvf.com
We call on the Document AI (DocAI) community to re-evaluate current methodologies and
embrace the challenge of creating more practically-oriented benchmarks. Document …
embrace the challenge of creating more practically-oriented benchmarks. Document …
On calibrating semantic segmentation models: analyses and an algorithm
We study the problem of semantic segmentation calibration. Lots of solutions have been
proposed to approach model miscalibration of confidence in image classification. However …
proposed to approach model miscalibration of confidence in image classification. However …
Cal-DETR: calibrated detection transformer
Albeit revealing impressive predictive performance for several computer vision tasks, deep
neural networks (DNNs) are prone to making overconfident predictions. This limits the …
neural networks (DNNs) are prone to making overconfident predictions. This limits the …
Beyond classification: Definition and density-based estimation of calibration in object detection
T Popordanoska, A Tiulpin… - Proceedings of the …, 2024 - openaccess.thecvf.com
Despite their impressive predictive performance in various computer vision tasks, deep
neural networks (DNNs) tend to make overly confident predictions, which hinders their …
neural networks (DNNs) tend to make overly confident predictions, which hinders their …
On calibration of object detectors: Pitfalls, evaluation and baselines
Reliable usage of object detectors require them to be calibrated—a crucial problem that
requires careful attention. Recent approaches towards this involve (1) designing new loss …
requires careful attention. Recent approaches towards this involve (1) designing new loss …
Calib3d: Calibrating model preferences for reliable 3d scene understanding
Safety-critical 3D scene understanding tasks necessitate not only accurate but also
confident predictions from 3D perception models. This study introduces Calib3D, a …
confident predictions from 3D perception models. This study introduces Calib3D, a …
Towards building self-aware object detectors via reliable uncertainty quantification and calibration
The current approach for testing the robustness of object detectors suffers from serious
deficiencies such as improper methods of performing out-of-distribution detection and using …
deficiencies such as improper methods of performing out-of-distribution detection and using …
Beyond probability partitions: Calibrating neural networks with semantic aware grouping
Research has shown that deep networks tend to be overly optimistic about their predictions,
leading to an underestimation of prediction errors. Due to the limited nature of data, existing …
leading to an underestimation of prediction errors. Due to the limited nature of data, existing …
Calibration for Long-tailed Scene Graph Generation
Miscalibrated models tend to be unreliable and insecure for downstream applications. In this
work, we attempt to highlight and remedy miscalibration in current scene graph generation …
work, we attempt to highlight and remedy miscalibration in current scene graph generation …