Learning CCA Representations for Misaligned Data - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Learning CCA Representations for Misaligned Data

Hichem Sahbi

Résumé

Canonical correlation analysis (CCA) is a statistical learning method that seeks to build view-independent latent representations from multi-view data. This method has been successfully applied to several pattern analysis tasks such as image-to-text mapping and view-invariant object/action recognition. However, this success is highly dependent on the quality of data pairing (i.e., alignments) and mispairing adversely affects the generalization ability of the learned CCA representations. In this paper, we address the issue of alignment errors using a new variant of canonical correlation analysis referred to as alignment-agnostic (AA) CCA. Starting from erroneously paired data taken from different views, this CCA finds transformation matrices by optimizing a constrained maximization problem that mixes a data correlation term with context regularization; the particular design of these two terms mitigates the effect of alignment errors when learning the CCA transformations. Experiments conducted on multi-view tasks, including multi-temporal satellite image change detection, show that our AA CCA method is highly effective and resilient to mispairing errors. Keywords
Fichier non déposé

Dates et versions

hal-02325827 , version 1 (22-10-2019)

Identifiants

Citer

Hichem Sahbi. Learning CCA Representations for Misaligned Data. European Conference on Computer Vision, ECCV - Workshop, Sep 2018, Munich, Germany. pp.468-485, ⟨10.1007/978-3-030-11018-5_39⟩. ⟨hal-02325827⟩
33 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More