Suchergebnisse - Computer Learning AND Pattern Recognition::Uncertainty Management

Deep Stereo Using Adaptive Thin Volume Representation With Uncertainty Awareness von Cheng, Shuo, Xu, Zexiang, Zhu, Shilin, Li, Zhuwen, Li, Li Erran, Ramamoorthi, Ravi, Su, Hao

“… We present Uncertainty-aware Cascaded Stereo Network (UCS-Net) for 3D reconstruction from multiple RGB images. Multi-view stereo (MVS …”
Volltext

Rainbow Memory: Continual Learning with a Memory of Diverse Samples von Bang, Jihwan, Kim, Heesu, Yoo, YoungJoon, Ha, Jung-Woo, Choi, Jonghyun

“… To enhance the sample diversity in the memory, we propose a novel memory management strategy based on per-sample classification uncertainty and data augmentation, named Rainbow Memory (RM …”
Volltext

Geometric Anchor Correspondence Mining with Uncertainty Modeling for Universal Domain Adaptation von Chen, Liang, Lou, Yihang, He, Jianzhong, Bai, Tao, Deng, Minghua

“… Therefore, in this paper, we propose a Geometric anchor-guided Adversarial and conTrastive learning framework with uncErtainty modeling called GATE to alleviate these issues …”
Volltext

Parameter-free Online Test-time Adaptation von Boudiaf, Malik, Mueller, Romain, Ayed, Ismail Ben, Bertinetto, Luca

“… Training state-of-the-art vision models has become prohibitively expensive for researchers and practitioners. For the sake of accessibility and resource reuse, …”
Volltext

Handling the impact of feature uncertainties on SVM: A robust approach based on Sobol sensitivity analysis von Zouhri, Wahb, Homri, Lazhar, Dantan, Jean-Yves

“… SVM is a supervised machine learning method for pattern recognition whose performance depends on the definition of its hyperparameters and the quality of data …”
Volltext

Exploring Data Aggregation in Policy Learning for Vision-Based Urban Autonomous Driving von Prakash, Aditya, Behl, Aseem, Ohn-Bar, Eshed, Chitta, Kashyap, Geiger, Andreas

“… Data aggregation techniques can significantly improve vision-based policy learning within a training environment, e.g …”
Volltext

Emerging artificial intelligence methods in structural engineering von Salehi, Hadi, Burgueño, Rigoberto

“… •The methods of pattern recognition, machine learning, and deep learning are studied.•The advantages of employing novel AI methods in structural engineering are discussed …”
Volltext

Transfer Knowledge from Head to Tail: Uncertainty Calibration under Long-tailed Distribution von Chen, Jiahao, Su, Bing

“… How to estimate the uncertainty of a given model is a crucial problem. Current calibration techniques treat different classes equally and thus implicitly assume …”
Volltext

Geometry and Uncertainty-Aware 3D Point Cloud Class-Incremental Semantic Segmentation von Yang, Yuwei, Hayat, Munawar, Jin, Zhao, Ren, Chao, Lei, Yinjie

“… Despite the significant recent progress made on 3D point cloud semantic segmentation, the current methods require training data for all classes at once, and …”
Volltext

Conformal deep forest for uncertainty-aware classification von Zhang, Jing, Qiu, Yunfei, Dong, Libo

“… Uncertainty in deep learning models significantly impacts their performance, robustness, and reliability, making explicit uncertainty quantification a critical research focus …”
Volltext

Source-Free Progressive Graph Learning for Open-Set Domain Adaptation von Luo, Yadan, Wang, Zijian, Chen, Zhuoxiao, Huang, Zi, Baktashmotlagh, Mahsa

“… , and failure to accurately estimate model predictions' uncertainty. To address these limitations, the Progressive Graph Learning (PGL …”
Volltext

Energy management strategy for battery/supercapacitor hybrid electric city bus based on driving pattern recognition von Shi, Junzhe, Xu, Bin, Shen, Yimin, Wu, Jingbo

“… During the online operation, the proposed EMS executes the designed driving pattern recognition algorithm with V2C assistance to select optimal control rules …”
Volltext

Improving Fishing Pattern Detection from Satellite AIS Using Data Mining and Machine Learning von de Souza, Erico N., Boerder, Kristina, Matwin, Stan, Worm, Boris

“… While coastal fisheries in national waters are closely monitored in some countries, existing maps of fishing effort elsewhere are fraught with uncertainty, especially in remote areas and the High Seas …”
Volltext

A novel algorithmic approach to model uncertainties associated with sustainable supply chain management using complex spherical fuzzy soft settings von Asghar, Ali, Khan, Khuram Ali, Rahman, Atiqe Ur, El-Morsy, Salwa

“… This study introduces the complex spherical fuzzy soft set (CSFSS), a sophisticated framework that deals with supplier selection uncertainties …”
Volltext

Uncertainty quantification in automated valuation models with spatially weighted conformal prediction von Hjort, Anders, Hermansen, Gudmund Horn, Pensar, Johan, Williams, Jonathan P.

“… Nonparametric machine learning models, such as random forests and gradient boosted trees, are frequently used to estimate house prices due to their predictive accuracy, but a main drawback …”
Volltext

Guidance for good practice in the application of machine learning in development of toxicological quantitative structure-activity relationships (QSARs) von Belfield, Samuel J., Cronin, Mark T.D., Enoch, Steven J., Firman, James W.

“… On account of the pattern-recognition capabilities of the underlying methods, the statistical power …”
Volltext

Active cluster annotation for wafer map pattern classification in semiconductor manufacturing von Shim, Jaewoong, Kang, Seokho, Cho, Sungzoon

“… •Active cluster annotation is proposed for wafer map pattern classification.•High-performance CNN is achieved with reduced annotation cost …”
Volltext

Data Uncertainty (DU)-Former: An Episodic Memory Electroencephalography Classification Model for Pre- and Post-Training Assessment von Wan, Xianglong, Liu, Zheyuan, Yao, Yiduo, Wan Hasan, Wan Zuha, Liu, Tiange, Duan, Dingna, Xie, Xueguang, Wen, Dong

“… Episodic memory training plays a crucial role in cognitive enhancement, particularly in addressing age-related memory decline and cognitive disorders …”
Volltext

Review of machine learning and WEAP models for water allocation under climate change von Hirko, Deme Betele, Du Plessis, Jakobus Andries, Bosman, Adele

“… It demonstrates how ML enhances WEAP’s capabilities by improving forecasting accuracy, recognising hydrological patterns, and reducing measurement uncertainties …”
Volltext

Bayesian Deep Learning for Spatial Interpolation in the Presence of Auxiliary Information von Kirkwood, Charlie, Economou, Theo, Pugeault, Nicolas, Odbert, Henry

“… Here, we demonstrate the power of feature learning in a geostatistical context by showing how deep neural networks can automatically learn the complex high-order patterns by which point …”
Volltext