[HTML][HTML] Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysis

B Lambert, F Forbes, S Doyle, H Dehaene… - Artificial Intelligence in …, 2024 - Elsevier
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 …

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 …

On calibrating semantic segmentation models: analyses and an algorithm

D Wang, B Gong, L Wang - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
We study the problem of semantic segmentation calibration. Lots of solutions have been
proposed to approach model miscalibration of confidence in image classification. However …

Cal-DETR: calibrated detection transformer

MA Munir, SH Khan, MH Khan, M Ali… - Advances in neural …, 2024 - proceedings.neurips.cc
Albeit revealing impressive predictive performance for several computer vision tasks, deep
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 …

On calibration of object detectors: Pitfalls, evaluation and baselines

S Kuzucu, K Oksuz, J Sadeghi, PK Dokania - European Conference on …, 2025 - Springer
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 …

Calib3d: Calibrating model preferences for reliable 3d scene understanding

L Kong, X Xu, J Cen, W Zhang, L Pan, K Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
Safety-critical 3D scene understanding tasks necessitate not only accurate but also
confident predictions from 3D perception models. This study introduces Calib3D, a …

Towards building self-aware object detectors via reliable uncertainty quantification and calibration

K Oksuz, T Joy, PK Dokania - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
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 …

Beyond probability partitions: Calibrating neural networks with semantic aware grouping

JQ Yang, DC Zhan, L Gan - Advances in Neural Information …, 2024 - proceedings.neurips.cc
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 …

Calibration for Long-tailed Scene Graph Generation

X Zhu, Y Xing, R Wang, Y Wang, X Lan - Proceedings of the 32nd ACM …, 2024 - dl.acm.org
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 …