PARTICUL: Part Identification with Confidence measure using Unsupervised Learning
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.
Cite
@article{arxiv.2206.13304,
title = {PARTICUL: Part Identification with Confidence measure using Unsupervised Learning},
author = {Romain Xu-Darme and Georges Quénot and Zakaria Chihani and Marie-Christine Rousset},
journal= {arXiv preprint arXiv:2206.13304},
year = {2022}
}
Comments
Accepted at XAIE: 2nd Workshop on Explainable and Ethical AI -- ICPR 2022