Uncertainty in Semantic Language Modeling with PIXELS
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Ensemble LearningSimilar Papers 제목 키워드 기반
Hyperbolic Uncertainty Aware Semantic Segmentation
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 SegmentationUncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentation
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+1Semantic World Models
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 AnsweringMAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model
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+10Uncertainty Quantification for Bird's Eye View Semantic Segmentation: Methods and Benchmarks
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