PARTICUL: Part Identification with Confidence measure using Unsupervised Learning

Romain Xu-Darme (1, 2) , Georges Quénot (2) , Zakaria Chihani (1) , Marie-Christine Rousset (3)

1 LSL - Laboratoire Sûreté des Logiciels
2 MRIM - Modélisation et Recherche d’Information Multimédia [Grenoble]
3 SLIDE - ScaLable Information Discovery and Exploitation [Grenoble]

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.

Mots clés: Part detection; Unsupervised learning; Interpretability; Confidence measure; Fine-grained recognition

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Apprentissage [cs.LG]

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⟩