The paper presents the first systematic evaluation of uncertainty quantification (UQ) methods applied to a foundation model for semantic segmentation. By fine‑tuning a lightweight DPT decoder on the pretrained SAM2 encoder, the authors benchmark four UQ approaches—Monte Carlo Dropout, Deep Sub‑Ensemble, Test‑Time Augmentation, and Evidential Deep Learning—across Cityscapes, NYUv2, and two out‑of‑domain settings, comparing segmentation accuracy, calibration, uncertainty quality, and inference time. The results reveal clear trade‑offs between predictive performance, reliability, and computational cost, underscoring both the promise and current limitations of uncertainty‑aware foundation models for real‑world deployment.
By Steven Landgraf, Joceline Hinz, Markus Ulrich
The paper presents the first systematic evaluation of uncertainty quantification (UQ) methods applied to a foundation model for semantic segmentation. By fine‑tuning a lightweight DPT decoder on the pretrained SAM2 encoder, the authors benchmark four UQ approaches—Monte Carlo Dropout, Deep Sub‑Ensemble, Test‑Time Augmentation, and Evidential Deep Learning—across Cityscapes, NYUv2, and two out‑of‑domain settings. The study compares segmentation accuracy, calibration, uncertainty quality, and inference time, revealing trade‑offs between predictive performance, reliability, and computational cost.
arXiv:2601.08355v3 Announce Type: replace
Abstract: Vision-Language Models (VLMs) are increasingly deployed in autonomous driving and embodied AI systems, where reliable perception is critical for sa...
By Guo Cheng, Huang Li
arXiv:2607. 01902v1 Announce Type: cross Abstract: Reliable confidence estimates are essential in semantic segmentation, especially in safety-critical settings where overconfident errors can mislead downstream decisions.
By Tristan Kirscher (ICube), Kim-Celine Kahl (DKFZ), Balint Kovacs (DKFZ), Maximilian R. Rokuss (DKFZ), Klaus Maier-Hein (DKFZ), Xavier Coubez (ICube), Philippe Meyer (ICube), Sylvain Faisan (ICube)
Reliable confidence estimates are essential in semantic segmentation, especially in safety-critical settings where overconfident errors can mislead downstream decisions. Yet modern segmentation models often remain miscalibrated.
arXiv:2606. 31603v1 Announce Type: cross Abstract: Semantic segmentation models struggle with data sparsity and rare or visually diverse regions, e.
By Nikolai R\"ohrich, Julian Glei{\ss}ner, Ahmed H. A. Ibrahim, Silvan Mertes, Tobias Huber
arXiv:2509. 10334v2 Announce Type: replace-cross Abstract: Vision Transformers (ViTs) have recently achieved strong results in semantic segmentation, yet their deployment on resource-constrained devices remains limited due to their high memory footprint and computational cost.
By Jordan Sassoon, Michal Szczepanski, Martyna Poreba
arXiv:2610.10116v1 Announce Type: new
Abstract: Semantic segmentation networks operate on a fixed set of classes and therefore fail when out-of-distribution (OOD) objects appear during deployment, a...
By Arnold Brosch, Abdelrahman Eldesokey, Michael Felsberg, Kira Maag
SenseFuse introduces a label‑free fusion approach that balances 2D image and 3D shape encoders for open‑vocabulary 3D instance segmentation. By selecting a scene‑level fusion weight through an adaptive, sensitivity‑based mechanism, it improves mask labeling accuracy across multiple datasets, recovering up to 93% of the potential gain from an oracle weight. The method demonstrates that image and shape encoders have complementary failure patterns, leading to higher instance AP in most evaluated settings.
By Euiseok Han, Tri Ton, Hwanhee Kim, Seungyeon Ryu, Chang D. Yoo
arXiv:2606. 18839v1 Announce Type: new Abstract: Vision-language models (VLMs) are now widely used in downstream tasks.
By Peiyu Yang, Paul Montague, Feng Liu, Andrew C. Cullen, Amardeep Kaur, Christopher Leckie, Sarah M. Erfani
arXiv:2607. 21137v1 Announce Type: cross Abstract: Independent sidewalk mobility is essential for blind and visually impaired pedestrians (BVIPs), yet smartphone-based assistive navigation requires perception models that distinguish walkable sidewalks from adjacent unsafe regions.
By Hakan Calim, Anamaria Dumitrescu, Adarsh Bhandary Panambur, Huzaifa Asif, Andreas Maier
SAFIRE is a large-scale benchmark for fire and smoke understanding in multimodal large language models (MLLMs), featuring 83,000 captioned images across 20 scenarios and 193,000 multiple-choice VQA questions derived from a 9.7K-image subset. The benchmark evaluates 10 dimensions of performance, from basic perception to higher-order reasoning, and employs a GPT‑5.4-assisted verification pipeline to ensure annotation quality. Experiments on ten open-source MLLMs (8B–38B) reveal an average accuracy of 61.9%, highlighting significant gaps in safety-critical reasoning, while fine-tuning vision encoders on just 7% of SAFIRE data boosts fire-scene classification accuracy from 20.1% to 64.5%. All resources are publicly available at https://risys-lab.github.io/SAFIRE/.
By Pengfei Li, Naufal Suryanto, Sicheng Zhang, Mohammad Alsharid, Muzammal Naseer