paper-with-me

홈 › Papers

Uncertainty in Semantic Language Modeling with PIXELS

2025-09-23 · Stefania Radu, Marco Zullich, Matias Valdenegro-Toro arxiv

Pixel-based language models aim to solve the vocabulary bottleneck problem in language modeling, but the challenge of uncertainty quantification remains open. The novelty of this work consists of analysing uncertainty and confidence in pixel-based language models across 18 languages and 7 scripts, all part of 3 semantically challenging tasks. This is achieved through several methods such as Monte Carlo Dropout, Transformer Attention, and Ensemble Learning. The results suggest that pixel-based models underestimate uncertainty when reconstructing patches. The uncertainty is also influenced by the script, with Latin languages displaying lower uncertainty. The findings on ensemble learning show better performance when applying hyperparameter tuning during the named entity recognition and question-answering tasks across 16 languages.

📄 PDF Abstract BibTeX arXiv:2509.19563

Code (0)

등록된 구현이 없습니다.

Tasks

Ensemble Learning

Similar Papers 제목 키워드 기반

Hyperbolic Uncertainty Aware Semantic Segmentation

2022-03-16 · Bike Chen, Wei Peng, Xiaofeng Cao, Juha Röning

Semantic segmentation (SS) aims to classify each pixel into one of the pre-defined classes. This task plays an important role in self-driving cars and autonomous drones. In SS, many works have shown that most misclassifi…

SegmentationSelf-Driving CarsSemantic Segmentation

Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentation

2021-12-14 · Yi Li, Yiqun Duan, Zhanghui Kuang, Yimin Chen 외

Weakly-Supervised Semantic Segmentation (WSSS) segments objects without a heavy burden of dense annotation. While as a price, generated pseudo-masks exist obvious noisy pixels, which result in sub-optimal segmentation mo…

Saliency DetectionSegmentationSemantic SegmentationWeakly supervised Semantic Segmentation+1

Semantic World Models

2025-10-22 · Jacob Berg, Chuning Zhu, Yanda Bao, Ishan Durugkar 외 arxiv

Planning with world models offers a powerful paradigm for robotic control. Conventional approaches train a model to predict future frames conditioned on current frames and actions, which can then be used for planning. Ho…

Visual Question Answering

MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model

2022-10-11 · CVPR 2023 1 · Yatai Ji, Junjie Wang, Yuan Gong, Lin Zhang 외

Multimodal semantic understanding often has to deal with uncertainty, which means the obtained messages tend to refer to multiple targets. Such uncertainty is problematic for our interpretation, including inter- and intr…

Contrastive LearningImage-text matchingImage-text RetrievalLanguage Modeling+10

Uncertainty Quantification for Bird's Eye View Semantic Segmentation: Methods and Benchmarks

2024-05-31 · Linlin Yu, Bowen Yang, Tianhao Wang, Kangshuo Li 외

The fusion of raw features from multiple sensors on an autonomous vehicle to create a Bird's Eye View (BEV) representation is crucial for planning and control systems. There is growing interest in using deep learning mod…

Autonomous DrivingBEV SegmentationBird's-Eye View Semantic SegmentationSegmentation+2