← Back to all news
arXiv Computer Vision By Baris Oguz, Xing Yao, Claudia Tawil, Alison Pouch, Brett Byram, Gabriel Arenas, Nadav Schwartz, Ipek Oguz

Segmentation Confidence for Arbitrary CNNs

Read the original on arXiv Computer Vision →

The paper presents a method for estimating segmentation confidence in convolutional neural networks without requiring custom architectures or retraining. It introduces voxel‑based uncertainty estimation that can be integrated into existing pipelines and proposes a novel technique to derive a single confidence score from uncertainty maps. Experiments across various regions of interest and imaging modalities demonstrate that the proposed score predicts segmentation performance on unseen data.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Machine Learning
Oct 15

Contrastive uncertainty learning for robust multi-structure segmentation in lower-pelvic MR

The paper introduces Contrastive Uncertainty Learning (CUL), a supervised framework that leverages voxel‑wise predictive uncertainty to guide representation learning for multi‑structure segmentation in lower‑pelvic MRI. Using Monte Carlo Dropout, CUL identifies uncertain voxels and shapes the embedding space so that low‑uncertainty, correctly predicted features become stable while high‑uncertainty or misclassified features are repelled, preventing feature collapse at challenging boundaries. Evaluated on 589 prostate MRI scans with a ViT‑based UperNet decoder, CUL achieves comparable Dice scores to a baseline while significantly reducing surface distance for most structures, and ablation studies confirm the necessity of both uncertainty‑guided sampling and the contrastive objective.

By Bilal Sidiqi, Yipei Wang, Wen Yan, Shaheer U. Saeed, Daniel C. Alexander, Yipeng Hu
ragcomputer-visionbenchmarkssafety
More like this →
arXiv AI
Aug 20

The Impact of CutMix on Reliability and Robustness in Semantic Segmentation

The paper investigates how the CutMix data augmentation technique affects reliability and robustness in semantic segmentation. It evaluates two architectures—CNN-based DeepLabV3+ and transformer-based SegFormer—on both in-domain and out-of-domain data. Results show that CutMix has a minor effect on segmentation accuracy but consistently improves reliability, especially under distribution shifts, by enhancing calibration and uncertainty quality.

By Steven Landgraf, Markus Ulrich
llmsagentscomputer-visionroboticssafety
More like this →