Uncertainty Learning

Uncertainty learning aims to quantify and manage uncertainty in machine learning models, improving their reliability and trustworthiness. Current research focuses on integrating uncertainty estimation into various tasks, including object detection, motion planning, and 3D reconstruction, often employing Bayesian frameworks, neural networks, and novel loss functions to model both data and model uncertainty. This work is crucial for deploying AI systems in safety-critical applications like autonomous driving and robotics, where understanding and mitigating uncertainty is paramount for reliable performance. Furthermore, improved uncertainty quantification enhances model interpretability and facilitates more robust decision-making in diverse fields.

Papers

September 26, 2024

ReliOcc: Towards Reliable Semantic Occupancy Prediction via Uncertainty Learning
Song Wang, Zhongdao Wang, Jiawei Yu, Wentong Li, Bailan Feng, Junbo Chen, Jianke Zhu
Uncertainty Calibration Semantic Occupancy Occupancy Network Uncertainty Learning

March 10, 2024

Robust Predictive Motion Planning by Learning Obstacle Uncertainty
Jian Zhou, Yulong Gao, Ola Johansson, Björn Olofsson, Erik Frisk
Motion Planning Robust Motion Planning Uncertainty Learning Uncertain Obstacle

February 29, 2024

NARUTO: Neural Active Reconstruction from Uncertain Target Observations
Ziyue Feng, Huangying Zhan, Zheng Chen, Qingan Yan, Xiangyu Xu, Changjiang Cai, Bing Li, Qilun Zhu, Yi Xu
Surface Reconstruction Uncertainty Learning Active Reconstruction Neural SLAM

January 8, 2024

Why does Prediction Accuracy Decrease over Time? Uncertain Positive Learning for Cloud Failure Prediction
Haozhe Li, Minghua Ma, Yudong Liu, Pu Zhao, Lingling Zheng, Ze Li, Yingnong Dang, Murali Chintalapati, Saravan Rajmohan, Qingwei Lin, Dongmei Zhang
Time Matter Failure Prediction Accuracy Loss Uncertainty Learning Disk Failure

July 18, 2023

Selective Generation for Controllable Language Models
Minjae Lee, Kyungmin Kim, Taesoo Kim, Sangdon Park
High Uncertainty Anticipation Generative Language Model Prediction Set Quantified Uncertainty Uncertainty Learning Set Prediction Network

June 19, 2023

UncLe-SLAM: Uncertainty Learning for Dense Neural SLAM
Erik Sandström, Kevin Ta, Luc Van Gool, Martin R. Oswald
Simultaneous Localization and Mapping Pixel Wise Uncertainty Uncertainty Learning Dense Simultaneous Localization

December 14, 2022

Post-hoc Uncertainty Learning using a Dirichlet Meta-Model
Maohao Shen, Yuheng Bu, Prasanna Sattigeri, Soumya Ghosh, Subhro Das, Gregory Wornell
Uncertainty Quantification Uncertainty Prediction Uncertainty Estimation Task Uncertainty Learning

October 24, 2022

Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval
Zhaopeng Dou, Zhongdao Wang, Weihua Chen, Yali Li, Shengjin Wang
Uncertainty Aware Uncertain Reasoning Data Uncertainty Predictive Reliability Text Based Person Retrieval Uncertainty Learning Low Quality Sample

October 6, 2022

Structure Representation Network and Uncertainty Feedback Learning for Dense Non-Uniform Fog Removal
Yeying Jin, Wending Yan, Wenhan Yang, Robby T. Tan
Uncertainty Map Haze Free Dehazing Method Uncertainty Learning

December 12, 2021

Few-shot Keypoint Detection with Uncertainty Learning for Unseen Species
Changsheng Lu, Piotr Koniusz
Keypoint Detector Keypoint Estimation Unseen Bird Specie Keypoints Representation Uncertainty Learning