Confidence Aware

Confidence-aware systems aim to improve the reliability and robustness of machine learning models by explicitly quantifying and utilizing prediction confidence. Current research focuses on developing methods to estimate confidence at various granularities (e.g., image-wide, instance-level, category-level), incorporating confidence into model training and decision-making processes (e.g., through confidence-weighted fusion, selective prediction, or dynamic thresholding), and using confidence to improve model calibration and address issues like overconfidence and distribution shift. This work is significant because it enhances the trustworthiness and safety of AI systems across diverse applications, from medical image analysis and robotics to natural language processing and advertising.

Papers

November 13, 2024

Confidence-aware Denoised Fine-tuning of Off-the-shelf Models for Certified Robustness
Suhyeok Jang, Seojin Kim, Jinwoo Shin, Jongheon Jeong
Native Robustness Adversarial Robustness Certified Robustness Confidence Aware Image Denoiser Shelf Model

September 12, 2024

Learning Rules from KGs Guided by Language Models
Zihang Peng, Daria Stepanova, Vinh Thinh Ho, Heike Adel, Alessandra Russo, Simon Ott
Language Model Confidence Aware Rule Learning Large Knowledge Graph Learning Rule KG BERTScore

August 2, 2024

Accelerating Domain-Aware Electron Microscopy Analysis Using Deep Learning Models with Synthetic Data and Image-Wide Confidence Scoring
Matthew J. Lynch, Ryan Jacobs, Gabriella Bruno, Priyam Patki, Dane Morgan, Kevin G. Field
Machine Learning Deep Learning Model Synthetic Data Synthetic Image Confidence Aware Feature Detection Confidence Scoring

July 10, 2024

Cross Domain Object Detection via Multi-Granularity Confidence Alignment based Mean Teacher
Jiangming Chen, Li Liu, Wanxia Deng, Zhen Liu, Yu Liu, Yingmei Wei, Yongxiang Liu
Confidence Aware Cross Domain Object Detection Granularity Alignment Mean Teacher

June 3, 2024

Confidence-Based Task Prediction in Continual Disease Classification Using Probability Distribution
Tanvi Verma, Lukas Schwemer, Mingrui Tan, Fei Gao, Yong Liu, Huazhu Fu
Deep Learning Model Continual LEArning Continual Learning Probability Distribution Confidence Aware Continual Text Classification Task Prediction

May 28, 2024

Confidence-aware multi-modality learning for eye disease screening
Ke Zou, Tian Lin, Zongbo Han, Meng Wang, Xuedong Yuan, Haoyu Chen, Changqing Zhang, Xiaojing Shen, Huazhu Fu
Multimodal Information Confidence Aware Retinal Disease Evidential Segmentation Eye Disease Screening

May 23, 2024

March 13, 2024

Extracting Explanations, Justification, and Uncertainty from Black-Box Deep Neural Networks
Paul Ardis, Arjuna Flenner
Deep Neural Network High Uncertainty Anticipation Black Box Confidence Aware DNN Inference Distribution Detection Task Justification Theory

March 6, 2024

Confidence-Aware Decision-Making and Control for Tool Selection
Ajith Anil Meera, Pablo Lanillos
External Control Decision Making Confidence Aware Tool Usage Metacognitive Difficulty Disentangling Confidence Score Distribution

February 27, 2024

February 19, 2024

February 16, 2024

Selective Prediction for Semantic Segmentation using Post-Hoc Confidence Estimation and Its Performance under Distribution Shift
Bruno Laboissiere Camargos Borges, Bruno Machado Pacheco, Danilo Silva
Semantic Segmentation Pre Trained Model System Performance Distribution Shift Confidence Aware Selective Prediction

December 29, 2023

ReliCD: A Reliable Cognitive Diagnosis Framework with Confidence Awareness
Yunfei Zhang, Chuan Qin, Dazhong Shen, Haiping Ma, Le Zhang, Xingyi Zhang, Hengshu Zhu
Ring Artifact Confidence Aware Confidence Measure Cognitive Diagnosis

July 22, 2023

Modality Confidence Aware Training for Robust End-to-End Spoken Language Understanding
Suyoun Kim, Akshat Shrivastava, Duc Le, Ju Lin, Ozlem Kalinli, Michael L. Seltzer
Language Understanding Pre Trained Automatic Speech Recognition End 2 End Confidence Aware Automatic Speech Recognition Hypothesis End to End Spoken Language

July 20, 2023

Investigating Low Data, Confidence Aware Image Prediction on Smooth Repetitive Videos using Gaussian Processes
Nikhil U. Shinde, Xiao Liang, Florian Richter, Michael C. Yip
Gaussian Process Confidence Bound Confidence Aware Image Prediction Visual Foresight Confidence Measure Continuous Video

May 21, 2023

Confidence-aware Personalized Federated Learning via Variational Expectation Maximization
Junyi Zhu, Xingchen Ma, Matthew B. Blaschko
Variational Inference Expectation Maximization Hierarchical Bayesian Confidence Aware

May 3, 2023

Distributional Instance Segmentation: Modeling Uncertainty and High Confidence Predictions with Latent-MaskRCNN
YuXuan Liu, Nikhil Mishra, Pieter Abbeel, Xi Chen
High Uncertainty Anticipation Instance Segmentation Object Recognition Object Mask Confidence Aware Mask RCNN High Confidence Prediction

Confidence Aware

Papers

Confidence-aware Denoised Fine-tuning of Off-the-shelf Models for Certified Robustness

Learning Rules from KGs Guided by Language Models

Accelerating Domain-Aware Electron Microscopy Analysis Using Deep Learning Models with Synthetic Data and Image-Wide Confidence Scoring

Cross Domain Object Detection via Multi-Granularity Confidence Alignment based Mean Teacher

Confidence-Based Task Prediction in Continual Disease Classification Using Probability Distribution

Confidence-aware multi-modality learning for eye disease screening

CEEBERT: Cross-Domain Inference in Early Exit BERT

Learning Multimodal Confidence for Intention Recognition in Human-Robot Interaction

Extracting Explanations, Justification, and Uncertainty from Black-Box Deep Neural Networks

Confidence-Aware Decision-Making and Control for Tool Selection

4CNet: A Diffusion Approach to Map Prediction for Decentralized Multi-robot Exploration

Confidence-Aware Multi-Field Model Calibration

Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models

BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts

Selective Prediction for Semantic Segmentation using Post-Hoc Confidence Estimation and Its Performance under Distribution Shift

ReliCD: A Reliable Cognitive Diagnosis Framework with Confidence Awareness

Modality Confidence Aware Training for Robust End-to-End Spoken Language Understanding

Investigating Low Data, Confidence Aware Image Prediction on Smooth Repetitive Videos using Gaussian Processes

Confidence-aware Personalized Federated Learning via Variational Expectation Maximization

Distributional Instance Segmentation: Modeling Uncertainty and High Confidence Predictions with Latent-MaskRCNN