PARTICUL: Part Identification with Confidence measure using Unsupervised Learning - Archive ouverte HAL Access content directly
Conference Papers Year :

PARTICUL: Part Identification with Confidence measure using Unsupervised Learning

(1, 2) , (2) , (1) , (3)
1
2
3

Abstract

In this paper, we present PARTICUL, a novel algorithm for unsupervised learning of part detectors from datasets used in fine-grained recognition. It exploits the macro-similarities of all images in the training set in order to mine for recurring patterns in the feature space of a pre-trained convolutional neural network. We propose new objective functions enforcing the locality and unicity of the detected parts. Additionally, we embed our detectors with a confidence measure based on correlation scores, allowing the system to estimate the visibility of each part. We apply our method on two public fine-grained datasets (Caltech-UCSD Bird 200 and Stanford Cars) and show that our detectors can consistently highlight parts of the object while providing a good measure of the confidence in their prediction. We also demonstrate that these detectors can be directly used to build part-based fine-grained classifiers that provide a good compromise between the transparency of prototype-based approaches and the performance of non-interpretable methods.
Fichier principal
Vignette du fichier
paper.pdf (3.63 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

cea-03703962 , version 1 (24-06-2022)

Identifiers

Cite

Romain Xu-Darme, Georges Quénot, Zakaria Chihani, Marie-Christine Rousset. PARTICUL: Part Identification with Confidence measure using Unsupervised Learning. 2-nd Workshop on Explainable and Ethical AI – ICPR 2022, Aug 2022, Montréal, Canada. ⟨cea-03703962⟩
74 View
31 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More