Don't miss the mismatch : investigating the objective function mismatch for unsupervised representation learning
Stuhr, Bonifaz (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)
Brauer, Jürgen (University of Applied Sciences Kempten. Department of Computer Science)

Fecha:	2022
Resumen:	Finding general evaluation metrics for unsupervised representation learning techniques is a challenging open research question, which recently has become more and more necessary due to the increasing interest in unsupervised methods. Even though these methods promise beneficial representation characteristics, most approaches currently suffer from the objective function mismatch. This mismatch states that the performance on a desired target task can decrease when the unsupervised pretext task is learned too long-especially when both tasks are ill-posed. In this work, we build upon the widely used linear evaluation protocol and define new general evaluation metrics to quantitatively capture the objective function mismatch and the more generic metrics mismatch. We discuss the usability and stability of our protocols on a variety of pretext and target tasks and study mismatches in a wide range of experiments. Thereby we disclose dependencies of the objective function mismatch across several pretext and target tasks with respect to the pretext model's representation size, target model complexity, pretext and target augmentations as well as pretext and target task types. In our experiments, we find that the objective function mismatch reduces performance by ∼ 0. 1-5. 0% for Cifar10, Cifar100 and PCam in many setups, and up to ∼ 25-59% in extreme cases for the 3dshapes dataset.
Nota:	Altres ajuts: acords transformatius de la UAB
Derechos:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, la comunicació pública de l'obra i la creació d'obres derivades, fins i tot amb finalitats comercials, sempre i quan es reconegui l'autoria de l'obra original.
Lengua:	Anglès
Documento:	Article ; recerca ; Versió publicada
Materia:	Objective function mismatch ; Metrics mismatch ; Unsupervised ; Self-supervised ; Representation learning ; Pattern recognition
Publicado en:	Neural Computing and Applications, Published online February 2022, ISSN 1433-3058

DOI: 10.1007/s00521-022-07031-9

13 p, 1.2 MB

El registro aparece en las colecciones:
Artículos > Artículos de investigación
Artículos > Artículos publicados