WAIL
发表于 2025-3-26 21:35:51
Quantification of Predictive Uncertainty via Inference-Time Samplingeterministic network without changes to the architecture nor training procedure. Experiments on regression tasks on imaging and non-imaging input data show the method’s ability to generate diverse and multi-modal predictive distributions and how estimated uncertainty correlates with prediction error.
HAUNT
发表于 2025-3-27 03:09:02
nnOOD: A Framework for Benchmarking Self-supervised Anomaly Localisation Methods. By isolating the synthetic, self-supervised task from the rest of the training process we perform a more faithful comparison of the tasks, whilst also making the workflow for evaluating over a given dataset quick and easy. Using this we have implemented the current state-of-the-art tasks and evaluated them on a challenging X-ray dataset.
意外的成功
发表于 2025-3-27 07:30:37
http://reply.papertrans.cn/95/9412/941132/941132_33.png
别名
发表于 2025-3-27 10:39:07
http://reply.papertrans.cn/95/9412/941132/941132_34.png
reception
发表于 2025-3-27 16:24:55
Stochastic Weight Perturbations Along the Hessian: A Plug-and-Play Method to Compute Uncertainty of models by sampling along the eigen directions of the Hessian of the converged minimum. We demonstrate the utility of our methods on two challenging medical ultrasound imaging problems - cardiac view recognition and kidney segmentation.
禁令
发表于 2025-3-27 17:46:26
http://reply.papertrans.cn/95/9412/941132/941132_36.png
暗讽
发表于 2025-3-27 22:55:53
Quantification of Predictive Uncertainty via Inference-Time Sampling that are trained to predict uncertainty estimates as variables of interest. These approaches require distinct architectural components and training mechanisms, may include restrictive assumptions and exhibit overconfidence, i.e., high confidence in imprecise predictions. In this work, we propose a
Hectic
发表于 2025-3-28 05:53:37
Uncertainty Categories in Medical Image Segmentation: A Study of Source-Related Diversitylping build confidence with end users, and for improving the training and performance of the networks. Several different methods have been proposed to estimate uncertainties, including those from epistemic (relating to the model used) and aleatoric (relating to the data) sources using test-time drop
痛苦一生
发表于 2025-3-28 08:12:37
http://reply.papertrans.cn/95/9412/941132/941132_39.png
色情
发表于 2025-3-28 13:13:59
What Do Untargeted Adversarial Examples Reveal in Medical Image Segmentation?tion tasks regardless of the ground truth. To explore and identify the uncertain regions, we propose a post-training method with untargeted adversarial examples where the input image is iteratively perturbed in a direction that maximizes the loss of original and perturbed prediction. The perturbed p