Object Detection with Probabilistic Guarantees: A Conformal Prediction Approach

Grancey, Florence De; Adam, Jean-Luc; Aleçu, Lucian; Gerchinovitz, Sébastien; Mamalet, Franck; Vigouroux, David

doi:10.1007/978-3-031-14862-0_23

Cited by 4 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They control the coordinates of the boxes but also the proposal and objectness scores, resulting in more and larger boxes. Finally, de Grancey et al (2022) proposed an extension of CP to OD, which will be the framework of choice in our exploratory study. 2 We would like to thank the author of the Youtube channel: https://www.youtube.com/@mika67407…”

Section: Uncertainty Quantification In Object Detectionmentioning

confidence: 99%

Conformal prediction for trustworthy detection of railway signals

Andéol,

Fel,

de Grancey

et al. 2024

AI Ethics

Self Cite

View full text Add to dashboard Cite

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

show abstract

Section: Uncertainty Quantification In Object Detectionmentioning

confidence: 99%

Conformal prediction for trustworthy detection of railway signals

Andéol,

Fel,

de Grancey

et al. 2024

AI Ethics

Self Cite

View full text Add to dashboard Cite

show abstract

“…The calibration set is used to estimate the thresholds needed to achieve the desired confidence levels. CP has been applied to a diverse set of applica-tions (e.g., image classification (Angelopoulos et al 2022), regression (Romano, Patterson, and Candes 2019), object detection (de Grancey et al 2022)).…”

Section: Related Workmentioning

confidence: 99%

Robust Uncertainty Quantification Using Conformalised Monte Carlo Prediction

Bethell,

Gerasimou,

Calinescu

2024

AAAI

View full text Add to dashboard Cite

Deploying deep learning models in safety-critical applications remains a very challenging task, mandating the provision of assurances for the dependable operation of these models. Uncertainty quantification (UQ) methods estimate the model’s confidence per prediction, informing decision-making by considering the effect of randomness and model misspecification. Despite the advances of state-of-the-art UQ methods, they are computationally expensive or produce conservative prediction sets/intervals. We introduce MC-CP, a novel hybrid UQ method that combines a new adaptive Monte Carlo (MC) dropout method with conformal prediction (CP). MC-CP adaptively modulates the traditional MC dropout at runtime to save memory and computation resources, enabling predictions to be consumed by CP, yielding robust prediction sets/intervals. Throughout comprehensive experiments, we show that MC-CP delivers significant improvements over comparable UQ methods, like MC dropout, RAPS and CQR, both in classification and regression benchmarks. MC-CP can be easily added to existing models, making its deployment simple. The MC-CP code and replication package is available at https://github.com/team-daniel/MC-CP.

show abstract