paper-with-me

홈 › Papers

A Latent Space Metric for Enhancing Prediction Confidence in Earth Observation Data

2024-01-30 · Ioannis Pitsiorlas, Argyro Tsantalidou, George Arvanitakis, Marios Kountouris, Charalambos Kontoes

This study presents a new approach for estimating confidence in machine learning model predictions, specifically in regression tasks utilizing Earth Observation (EO) data, with a particular focus on mosquito abundance (MA) estimation. We take advantage of a Variational AutoEncoder architecture, to derive a confidence metric by the latent space representations of EO datasets. This methodology is pivotal in establishing a correlation between the Euclidean distance in latent representations and the Absolute Error (AE) in individual MA predictions. Our research focuses on EO datasets from the Veneto region in Italy and the Upper Rhine Valley in Germany, targeting areas significantly affected by mosquito populations. A key finding is a notable correlation of 0.46 between the AE of MA predictions and the proposed confidence metric. This correlation signifies a robust, new metric for quantifying the reliability and enhancing the trustworthiness of the AI model's predictions in the context of both EO data analysis and mosquito abundance studies.

📄 PDF Abstract BibTeX arXiv:2401.17342

Code (0)

등록된 구현이 없습니다.

Tasks

Earth Observation

Methods 이 논문이 사용한 방법론

AE An autoencoder is a type of artificial neural network used to learn efficient data codings in an unsupervised manner. The aim of an autoencoder is to learn a representation…
Focus 설명 없음

Similar Papers 제목 키워드 기반

Trustworthy Intrusion Detection: Confidence Estimation Using Latent Space

2024-09-19 · Ioannis Pitsiorlas, George Arvanitakis, Marios Kountouris

This work introduces a novel method for enhancing confidence in anomaly detection in Intrusion Detection Systems (IDS) through the use of a Variational Autoencoder (VAE) architecture. By developing a confidence metric de…

Anomaly DetectionBinary ClassificationIntrusion Detection

Uncertainty Quantification in Deep Neural Networks through Statistical Inference on Latent Space

2023-05-18 · Luigi Sbailò, Luca M. Ghiringhelli

Uncertainty-quantification methods are applied to estimate the confidence of deep-neural-networks classifiers over their predictions. However, most widely used methods are known to be overconfident. We address this probl…

Uncertainty Quantification

Calibrated neighborhood aware confidence measure for deep metric learning

2020-06-08 · Maryna Karpusha, Sunghee Yun, Istvan Fehervari

Deep metric learning has gained promising improvement in recent years following the success of deep learning. It has been successfully applied to problems in few-shot learning, image retrieval, and open-set classificatio…

Few-Shot LearningImage RetrievalMetric LearningRetrieval

Improving Explainability of Softmax Classifiers Using a Prototype-Based Joint Embedding Method

2024-07-02 · Hilarie Sit, Brendan Keith, Karianne Bergen

We propose a prototype-based approach for improving explainability of softmax classifiers that provides an understandable prediction confidence, generated through stochastic sampling of prototypes, and demonstrates poten…

Explainable Artificial Intelligence (XAI)Out-of-Distribution Detection

Generate Novel Molecules With Target Properties Using Conditional Generative Models

2020-09-15 · Abhinav Sagar

Drug discovery using deep learning has attracted a lot of attention of late as it has obvious advantages like higher efficiency, less manual guessing and faster process time. In this paper, we present a novel neural netw…

DecoderDrug DiscoveryProperty Prediction